VoIP.ms Wiki - New pages [en]

Catelaya - Orchid Link SBC

2026-06-23T18:28:39Z

Scomtois: moved Catalaya - Orchid Link SBC to Cataleya - Orchid Link SBC

[[File:Cataleya logo.png|400px|right|none]]

This article provides general configuration guidelines for connecting an '''Orchid Link Session Border Controller (SBC)''' with [[VoIP.ms]] SIP trunking. The configuration described below focuses on two Orchid Link zones:

:* '''Access Public''': VoIP.ms-facing side of the SBC.
:* '''Access Core''': customer network, SIP platform, IP-PBX, softswitch, or core-facing side of the SBC.

'''Audience:''' Network and voice engineers familiar with SIP, VoIP.ms accounts, and basic Orchid Link administration.

'''Vendor confirmation pending:''' Supported Orchid Link software versions and deployment models should be confirmed with Cataleya before adding a component information table to this article.

'''Note:''' The screenshots and field values shown in this article are examples only. Adjust the configuration according to your own network design, security policy, licensing, and Orchid Link deployment.

'''The Microsoft Teams section is a high-level overview and may require additional configuration and testing.'''

__TOC__

= Prerequisites =

Before starting the configuration, make sure you have the following information available:

:* Access to the Orchid Link administrative interface.
:* A configured customer and partition in Orchid Link.
:* SIP and media interfaces already created for both the public and core sides.
:* The VoIP.ms server or POP information that will be used by the trunk.
:* The trusted VoIP.ms source IP addresses or POPs that will be allowed through the SBC security rules.
:* SIP credentials or trunk information required for the VoIP.ms side.
:* The internal IP address and SIP port of the customer-side PBX, softswitch, or SIP platform.
:* Any required SIP Parameters, Transparency, Media, Call Admission Control, and Routing Policy profiles.

= Configuration Overview =

The Orchid Link SBC configuration is separated into two main zones:

:* Configure the '''Access Public''' zone first. This zone represents the VoIP.ms-facing side of the SBC.
:* Configure the '''Access Core''' zone after the Access Public zone. This zone represents the customer network or PBX-facing side of the SBC.

Once both zones are created, routing is configured so that calls can pass between the VoIP.ms side and the core-side SIP environment.

= Access Public Zone Configuration =

The Access Public zone is the side of the SBC that communicates with VoIP.ms. This zone should be configured first.

== Step 1 - General ==

In the '''General''' tab, configure the mandatory fields shown in the Orchid Link interface.

[[File:Orchid_Link_Access_Public_General.png|thumb|600px|Access Public zone - General tab]]

:* '''Name''': Enter a descriptive name for the zone, for example, '''VoIPMS_Public'''.
:* '''Customer''': Select the customer associated with this zone.
:* '''Partition''': Select the partition allocated to this customer.
:* '''Zone Type''': Select '''AccessPublic'''.
:* '''Time Zone''': Select the appropriate time zone for the customer.
:* '''Trunk Group Type''': Leave this set to '''None''', unless your deployment requires another value.
:* '''Service Level''': Keep the default service level, for example, '''Gold''', unless your policy requires otherwise.

== Step 2 - Signaling ==

In the '''Signaling''' step, select the SIP-related profiles and interfaces used for the VoIP.ms-facing side.

[[File:Orchid_Link_Access_Public_Signaling.png|thumb|600px|Access Public zone - Signaling step]]

:* '''SIP Profile''': Select the preconfigured SIP Parameters Profile from the drop-down list.
::* This profile is created under '''Profiles > SIP Parameters'''.

[[File:Orchid_Link_SIP_Parameters_Profile.png|thumb|600px|SIP Parameters Profile example]]

:* '''Transparency Profile''': Select the transparency profile created for this deployment.
::* This profile can be created under '''Profiles > Transparency'''.

[[File:Orchid_Link_Transparency_Profile.png|thumb|500px|Transparency Profile example]]

:* '''SIP Interface''': Select the SIP Interface configured for the public access side and add it to the zone.

== Step 3 - Media ==

In the '''Media''' step, select the media interface and media profile used for VoIP.ms traffic.

[[File:Orchid_Link_Access_Public_Media.png|thumb|600px|Access Public zone - Media step]]

:* '''Media Interface''': Select the Media Interface configured for the public access side and add it to the zone.
:* '''Media Profile''': Select the Media Profile used for VoIP.ms traffic.
::* The Media Profile is created under '''Profiles > Media'''.

[[File:Orchid_Link_Media_Profile.png|thumb|500px|Media Profile example]]

== Step 4 - Call Admission Control ==

In the '''Call Admission Control''' step, select the CAC profile that will control the number of concurrent sessions allowed for this zone.

[[File:Orchid_Link_CAC_Profile_Zone.png|thumb|450px|Zone CAC Profile example]]

:* '''CAC Profile Zone''': Select the CAC profile created for this zone.
::* The profile is created under '''Profiles > Call Admission Control'''.
::* Configure the session count according to the licensed capacity allocated for VoIP.ms traffic.
:* '''CAC Profile UE''': Select the UE CAC profile if you want to apply per-endpoint limits.

[[File:Orchid_Link_CAC_Profile_UE.png|thumb|450px|UE CAC Profile example]]

== Step 5 - Security ==

In the '''Security''' step, configure the allowed sources and any required security parameters according to your security policy.

[[File:Orchid_Link_Access_Public_Security.png|thumb|600px|Access Public zone - Security step]]

:* Restrict access to known and trusted VoIP.ms IP addresses or POPs whenever possible.
:* Avoid allowing unrestricted public SIP access unless this is specifically required and properly secured.
:* Apply any additional SBC security settings required by your deployment.

== Step 6 - Remote Peers ==

No configuration is required in this step for the Access Public zone.

:* Leave the default values unless a specific deployment requires otherwise.

== Step 7 - Routing ==

In the '''Routing''' step, define where traffic from the Access Public zone should be sent.

[[File:Orchid_Link_Access_Public_Routing.png|thumb|600px|Access Public zone - Routing step]]

:* '''Egress Zone''': Select the '''Access Core''' zone as the egress destination for this Access Public zone.

== Step 8 - Transcoding ==

If transcoding is not required, no configuration is needed in this step.

:* Configure transcoding only if codec interworking is required between VoIP.ms and the customer-side SIP environment.
:* The transcoding profile should match your network design and licensing.

= Access Core Zone Configuration =

The Access Core zone represents the customer network or PBX-facing side of the SBC. Configure this zone after the Access Public zone has been created.

== Step 1 - General ==

In the '''General''' tab, configure the core-side zone information.

:* '''Zone Type''': Select '''AccessCore'''.
:* '''Name''': Use a clear name that identifies the customer or core-side environment.
:* '''Customer''': Select the relevant customer.
:* '''Partition''': Select the partition allocated to the customer.
:* '''Time Zone''': Select the appropriate time zone.
:* '''Trunk Group Type''': Leave as '''None''', unless your deployment requires otherwise.
:* '''Service Level''': Use the appropriate service level for the customer or deployment.

== Step 2 - Signaling ==

In the '''Signaling''' step, configure the SIP interface and profiles used toward the customer core network.

:* '''SIP Interface''': Select the SIP Interface configured for the core side.
:* '''SIP Profile''': Select the appropriate SIP Parameters Profile for the core network.
::* This profile may be different from the profile used on the VoIP.ms-facing side.
:* '''Transparency Profile''': Select the appropriate transparency profile.
::* This profile can be created under '''Profiles > Transparency'''.

== Step 3 - Media ==

In the '''Media''' step, configure the media interface and media profile used toward the core network.

:* '''Media Interface''': Select the Media Interface configured for the core side.
:* '''Media Profile''': Select the Media Profile used for traffic toward the core network (customer network or PBX).

== Step 4 - Call Admission Control ==

In the '''Call Admission Control''' step, select the CAC profile used for the core-facing side.

:* '''CAC Profile Zone''': Select the core-side CAC Profile Zone.
::* Configure the session count according to the capacity you want to reserve for core-side calls.
:* '''CAC Profile UE''': Select the UE CAC profile if per-endpoint limits are required on the core side.

== Step 5 - Security ==

In the '''Security''' step, configure the allowed source addresses for the core-side signaling devices.

:* Only allow traffic from trusted internal networks, or core devices
:* Do not expose the core-side zone to untrusted networks unless this is part of the intended design and is properly secured.

== Step 6 - Remote Peers ==

In the '''Remote Peers''' step, configure the customer-side SIP endpoint information.

[[File:Orchid_Link_Access_Core_Remote_Peers.png|thumb|600px|Access Core zone - Remote Peers step]]

:* '''Remote Endpoints''': Configure the IP address and port of the remote core endpoint.
::* Examples include an IP-PBX, softswitch, SIP application server, or another SBC.
::* The Orchid Link SBC will send SIP signaling to these addresses.

== Step 7 - Routing ==

In the '''Routing''' step, select the routing policy that will be used for traffic toward the core side.

[[File:Orchid_Link_Access_Core_Routing.png|thumb|600px|Access Core zone - Routing step]]

:* '''Routing Policy''': Select the appropriate Session Routing Policy from the drop-down list.
::* The policy is configured under '''Policy Configuration > Session Routing Policies'''.

[[File:Orchid_Link_Session_Routing_Policy.png|thumb|600px|Session Routing Policy example]]

== Step 8 - Transcoding ==

Configure transcoding only if codec interworking is required between VoIP.ms and your core network.

:* If transcoding is not required, no changes are needed in this step.
:* If transcoding is required, select or create the appropriate transcoding profile according to the deployment requirements.

= Final Checklist =

After completing the configuration, review the following items:

:* The Access Public zone is configured as '''AccessPublic'''.
:* The Access Core zone is configured as '''AccessCore'''.
:* SIP and media interfaces are assigned to the correct zones.
:* The Access Public zone routes traffic toward the Access Core zone.
:* The Access Core zone has the correct remote endpoint configured.
:* The Session Routing Policy is selected and points to the intended routing behavior.
:* Security rules only allow trusted VoIP.ms sources and trusted core-side devices.
:* CAC limits match the licensed and intended concurrent call capacity.
:* Transcoding is configured only when required.

Grandstream HT801v2

2026-06-18T16:00:58Z

Scomtois:

This guide explains how to configure a '''Grandstream HandyTone HT801v2''' for use with VoIP.ms services. The HT801v2 is a compact, single-port Analog Telephone Adapter (ATA) that allows users to connect a traditional analog phone or fax machine to the VoIP.ms network. Along with the two-port HT802v2 and their previous-generation counterparts, it has remained one of the [[ATA Devices#Most Popular ATA Devices|most commonly used ATA devices]] among VoIP.ms customers in recent years, based on internal network analytics.

=== Device details ===
The HT801v2 is an easy-to-use, single-port Analog Telephone Adapter (ATA) designed for residential users, small offices, and large-scale commercial IP voice deployments.
Featuring an ultra-compact form factor measuring 10×10×2.95cm and weighing 102g, the device provides a simple and cost-effective way to integrate a traditional analog telephone or fax machine into a modern VoIP environment. Despite its small size, the HT801v2 offers a comprehensive feature set, including:

* Support for a single SIP profile through a dedicated FXS (RJ11) port, compatible with both [[Order a DID Number|VoIP.ms DIDs]] and [[Sub Accounts|sub-accounts]]
* Incoming and outgoing [[Caller ID]] with support for a wide range of caller ID formats
* A 10/100 Mbps auto-sensing Ethernet (RJ45) network port
* Automatic SIP server failover to maintain service continuity should the primary server become unavailable
* Advanced telephony features including call transfer, [[Call Forwarding|call forwarding]], call waiting, hold, do-not-disturb, message waiting indication, multilingual prompts, and flexible dialplans
* Optional [[Call Encryption - TLS/SRTP|TLS and SRTP encryption protocols]] to secure calls and accounts
* [[Virtual Fax|Fax over IP capability]] using T.38 fax relay with automatic fallback to G.711 pass-through

<gallery caption="Grandstream HandyTone HT801v2 photos (click to expand)" heights="224" perrow="3" widths="224" style="margin: 1.5em auto; text-align: center; width: fit-content;">
File:Grandstream HandyTone HT801v2 - Front View.png|Front view
File:Grandstream HandyTone HT801v2 - Top View.png|Top view, showing status LEDs for power, network connection, and in-use indicator for both analog phone ports
File:Grandstream HandyTone HT801v2 - Rear View.png|Rear view with Ethernet and dual phone ports, USB Micro-B power input and pinhole reset
</gallery>

== Configuring your device ==
[[File:HT801v2 FXS1 General Settings AccountRegistration.png|thumb|right|512px|FXS Port 1 General Settings > Account Registration]]

=== Prerequisites ===
* Grandstream HT801v2
:* Latest firmware installed ([https://www.grandstream.com/support/firmware|check Grandstream site]) ''(We you use firmware version 1.0.11.4 or later.)''
:* VoIP.ms account with a configured DID and a sub-account
:* Internet access via Ethernet
:* Phone or fax device connected to FXS Port 1

=== Logging into the web interface ===
: Connect the HT801v2 to your network and power it on.
::* Pick up the connected phone, dial: <code style="background-color: #eee; border: thin solid #ccc; color: #000; font-family: monospace; padding: 1px 4px;">* * * 0 2</code> (Star Star Star 0 2)

The ATA will read its IP address.
Open a browser and go to that IP (e.g., http://192.168.1.50).
: Login
:* Username: <code>admin</code>
:* Password: found on device label (or as set by you)

=== General Settings (FXS PORT1) ===
[[File:HT801v2 FXS1 General Settings NetworkSettings.png|thumb|right|512px|FXS Port 1 General Settings > Network Settings]]

==== Account Registration ====
:* '''Account Active:''' ✅ Checked
:* '''Primary SIP Server''': popserver.voip.ms (or your nearest VoIP.ms POP) ''eg: montreal1.voip.ms''
:* '''Prefer Primary SIP Server''' Yes
:* '''Outbound Proxy''' popserver.voip.ms (Same as the Primary SIP Server)
:* ''Backup Outbound Proxy This is optional you can enter a different VoIP.ms PoP Server location. eg: toronto2.voip.ms''
::* ''Prefer Primary Outbound Proxy: Check the box, only if you entered a backup Outbound Proxy''
:* '''SIP User ID''' Your VoIP.ms sub-account username
:* '''SIP Authenticate ID''' Same as SIP User ID
:* '''SIP Authentication Password''' Your sub-account password

==== Network Settings ====
:* '''DNS Mode''': A Record
:* '''NAT Traversal''' Keep-Alive
: Click '''Save and Apply'''.

=== SIP Settings Tab ===
[[File:Grandstream HT801v2 FXS Port1 Advanced Settings.png|thumb|right|512px|FXS Port 1 Advanced Settings > Security Settings]]

==== SIP Basic settings ====
:* '''SIP Registration''': Yes
:* '''Register Expiration''': 2 (minutes)
:* '''Enable SIP OPTIONS Keep Alive''': Yes
:* Local SIP Port: 5060 (change if multiple ATAs)

: Disable extra headers:
:* '''Privacy Header''' → No
:* '''P-Preferred-Identity Header''' → No
:* '''P-Access-Network-Info''' → No
:* '''P-Emergency-Info''' → No

==== Codec Settings Tab ====
: '''Preferred Vocoder''' (in all sessions): G722, (G.711 μ-law) then set G711 for the rest.

==== Advanced Settings ====
: '''Check SIP User ID for Incoming INVITE''': Enabled
: '''Allow incoming SIP messages from SIP proxy only''': Enabled

==== Faxing ====
[[File:Grandstream HT80v2 FXS Port1 Call Freatures Settings.png|thumb|right|512px|FXS Port 1 Call Features Settings]]
: Ensure options like Enable‑Call‑Waiting, Caller‑ID, and Tone are unchecked — avoiding disruptions during fax sessions.
: Security Settings: Enable Allow incoming packets from SIP proxy only to restrict access to VoIP.ms servers.

: Under '''Call Settings'''
: '''Disable Local Call Features''': Yes
:* '''Enable-Call-Waiting''': uncheck
:* '''Enable-Call-Waiting-Caller-ID''': uncheck
:* '''Enable-Call-Waiting-Tone''': uncheck

: Under '''Call Features Settings''':
:* Set ''' Enable Local Call Features''' '''No''' to prevent unintended feature code usage via the fax machine.

: Under '''Codec Settings''':
::* '''Fax Mode''': T.38 (if you are using it for faxing with a VoIP.ms FAX POP server)
::* '''T.38 Max Bit Rat'''e: 14400 bps
::* '''Jitter Buffer''': Fixed, High

: Under '''Analog Signal Line Configuration'''
::* '''Enable Line Echo Canceller (LEC)''' → Check

== Testing ==
: Reboot the ATA after applying settings.
: Check '''Status tab''' → Registration should be '''Yes'''.
: Dial: <code style="background-color: #eee; border: thin solid #ccc; color: #000; font-family: monospace; padding: 1px 4px;">4443</code> for a Voice Echo Test.

== External links ==
* [https://www.grandstream.com/products/gateways-and-atas/analog-telephone-adaptors/product/ht801v2 Official product page]
* [https://www.grandstream.com/hubfs/Product_Documentation/HT801%20V2/Datasheet_HT801_V2_English.pdf Product datasheet and specifications] (PDF)
* [https://documentation.grandstream.com/article-categories/ht8xx-series Grandstream Documentation Center]
** [https://documentation.grandstream.com/knowledge-base/ht801-v2-quick-installation-guide/ HT801v2 Quick Installation Guide]
** [https://documentation.grandstream.com/knowledge-base/ht80x-v2-administration-guide/ HT801v2 Administration Guide]
** [https://documentation.grandstream.com/knowledge-base/ht80x-v2-user-guide/ HT801v2 User Guide]
* [https://www.grandstream.com/support/firmware Firmware download site]

[[Category:Analog Telephone Adapters]]

Mitel 6900 Series SIP Phones

2026-06-13T02:20:31Z

Scomtois:

[[File:Mitel_6900_Series.png|right|none|Mitel 6900 Series IP Phones]]
This guide explains how to configure a Mitel 6900 Series Open SIP phones with VoIP.ms.
Please note that menu names and available options may vary depending on the phone model, firmware version, and provisioning method being used.

= Supported Models =
This guide applies generally to Mitel 6800 and 6900 Series IP phones, including but not limited to:
:* 6863i
:* 6865i
:* 6867i
:* 6869i
:* 6873i
:* 6905
:* 6907
:* 6910
:* 6915
:* 6920/6920w
:* 6930/6930w
:* 6940/6940w
:* 6970
:* M695 PKM ''(If supported)''

= Firmware Note =
<div style="position: relative; width: 90%; /* height: 20px; */ background-color: #f0fbff; border: 2px solid #2f6185; border-radius: 8px; padding: 12px; overflow: hidden; display: flex; align-items: left; justify-content: left; flex-wrap: wrap; text-align: stretch; font-family: sans-serif; color: #333;">
<div style="position: absolute; margin-top:35px; margin-left: 20px; font-size: 150px; opacity: 0.1; z-index: 1; pointer-events: none; user-select: none; transform: rotate(-20deg);">ℹ️</div>
<p style="position: relative; z-index: 2; margin: 0; line-height: 1.5;">

:'''The phone must be running SIP firmware.'''
:'''If the phone was previously used with another platform or PBX, make sure it is running SIP firmware before attempting to register it with VoIP.ms.'''
:'''If the phone is not running SIP firmware, please refer to the manufacturer documentation for firmware conversion or firmware upgrade instructions.'''
</p></div>

= Step 1 - Create or Verify the VoIP.ms Sub Account =
Access your VoIP.ms Customer Portal:
:# Go to <code>Sub Accounts</code>
:# Create a new '''Sub Account''' or edit an existing one
:# Take note of the '''SIP Username and SIP Password'''
:# Make sure the selected codec matches the codec configured on the phone
:# Save the changes
:::Recommended Sub Account settings:
::::'''Device Type:''' ATA Device, IP Phone or Softphone
::::'''SIP Username:''' Your Sub Account username <code>100000_office</code>
::::'''Password:''' Your SIP password
::::'''Protocol:''' SIP
::::'''Allowed Codecs:''' Select the codecs you will use on the Mitel phone

= Step 2 - Obtain the Phone IP Address =
Connect the phone to the network and power it on.
From the phone keypad or screen:
:# Press the <code>Settings</code> button
:# Navigate to <code>Status</code>
:# Go to <code>Network</code>
:# Locate the phone IP address

:The path may appear as:
:: <pre>Settings -> Status -> Network -> IP Address</pre>
:: On some models, the IP address may be located under:
:: <pre>Phone Status -> IP & MAC Addresses</pre>

= Step 3 - Access the Phone Web Interface =
From a computer connected to the same network as the phone:
:# Open a web browser
:# Enter the phone IP address in the address bar
:# Log in as administrator

Default administrator credentials are commonly:
: '''Username:''' <code>admin</code>
: '''Password:''' <code>22222</code>

'''Note:'''
:If these credentials do not work, the password may have been changed by a previous administrator. In that case, please refer to the device documentation or reset procedure.

'''Security recommendation:'''
:It is strongly recommended to change the default administrator password after completing the configuration.

= Step 4 - Configure SIP Line 1 =
Once logged into the phone Web Interface:
:# Go to <code>Advanced Settings</code>
:# Select <code>Line 1</code>

The SIP settings are usually divided into two main sections:
:* Basic SIP Authentication Settings
:* Basic SIP Network Settings

== Basic SIP Authentication Settings ==
Under <code>Basic SIP Authentication Settings</code>, configure the following fields:
:'''Screen Name:''' Name that displays on the idle screen
:'''Screen Name 2:''' Custom text message that displays on the idle screen.
:: [[File:Mitel_6900_ScreenName.png|none|350px]]
:'''Phone Number:''' Enter your VoIP.ms SubAccount Username <code>######_SubAccount</code>
:'''Authentication Name:''' Enter your VoIP.ms SubAccount Username <code>######_SubAccount</code>
:'''Password:''' Use the SIP password from the Main Account or Sub Account.
:'''Display Name:''' Enter your outbound Caller ID Name that will be displayed for Canadian Numbers

<div style="position: relative; width: 90%; /* height: 20px; */ background-color: #fff3cd; border: 2px solid #ffeeba; border-radius: 8px; padding: 12px; overflow: hidden; display: flex; align-items: left; justify-content: left; flex-wrap: wrap; text-align: stretch; font-family: sans-serif; color: #856404;">
<div style="position: absolute; margin-top:35px; margin-left: 20px; font-size: 150px; opacity: 0.1; z-index: 1; pointer-events: none; user-select: none; transform: rotate(-20deg);">⚠️</div>
<p style="position: relative; z-index: 2; margin: 0; line-height: 1.5;">

:- We suggest entering your outbound Caller ID Name must be in '''CAPITAL LETTERS'''. This will appears more clearly/visible on some devices.
:- You must '''NOT''' use any special characters, they will not be displayed.
:- '''Do not exceed 15 characters'''. Some of regular Canadian providers will '''not''' show more than 15 characters. We suggest shrinking or adapt your caller ID.
:- Spaces are allowed and count as a character.
</p></div>

:: [[File:Mitel_6900_Line1_Basic_SIP_Auth.png|none|500px]]

== Basic SIP Network Settings ==
Under <code>'''Basic SIP Network Settings'''</code>, configure the following fields:
:'''Proxy Server:''' Enter your Preferred VoIP.ms PoP server. ''Example: <code>montreal3.voip.ms</code>''
:'''Proxy Port:''' <code>5060</code> ''(This is the default SIP port.)''

:'''Outbound Proxy:''' Enter your Preferred VoIP.ms PoP server. ''Example: <code>montreal3.voip.ms</code>''
:'''Proxy Port:''' <code>5060</code> ''(This is the default SIP port.)''

:'''Registrar Server:''' Enter your Preferred VoIP.ms PoP server. ''Example: <code>montreal3.voip.ms</code>''
:'''Registrar Port:''' <code>5060</code> ''(This is the default SIP port.)''

:'''Registration Period:''' <code>120</code> ''secondes''
:: Recommended registration expiry value.

:: [[File:Mitel_6900_Line1_Basic_SIP_Network.png|none|500px]]

== Step 5 - Save the Configuration ==
After entering the '''SIP authentication''' and '''SIP network settings''':
:# Click''' <code>Save Settings</code>'''
:# Reboot the phone if required
:# Wait for the phone to register

The phone should show the line as registered once the configuration is successful.

= Codec Settings =
You can change the default codecs selection on the phone to match the codecs enabled in your VoIP.ms account or Sub Account.
: '''Note''': This is optional, as the Basic Codecs Includes G.711u.

= Firewall and NAT Considerations =
Recommended router settings:
:* Disable SIP ALG
:* Make sure the phone can resolve DNS hostnames
:* Make sure the phone can reach the selected VoIP.ms server
:* Avoid multiple SIP devices using the same local SIP port when possible

= Test Calls =
After the phone registers, test the configuration.
: VoIP.ms test numbers:
:* '''4443:''' Echo test
:* '''4747:''' DTMF test
:* '''822:''' Caller ID playback test
:* '''*98''' or '''*97''': Voicemail access

It is also recommended to test:
:* Outbound calls
:* Inbound calls
:* Two-way audio
:* DTMF through an IVR
:* Voicemail access

= Troubleshooting =
== The Phone Does Not Register ==
If the phone does not register, verify the following:
:* The SIP Username is correct
:* The SIP Password is correct
:* The correct VoIP.ms PoP server is being used
:* The SIP port is correct
:* The selected transport protocol matches the account configuration
:* SIP ALG is disabled on the router
:* The account or Sub Account is not blocked due to repeated failed registration attempts
:* If using SIP-TLS, encrypted SIP traffic is enabled in the VoIP.ms portal and the phone is configured for TLS/SRTP

== Incoming Calls Do Not Reach the Phone ==
If outbound calls work but inbound calls do not, verify the following:
:* The DID is routed to the correct SIP account or Sub Account
:* The DID PoP matches the server used by the phone
:* The phone is currently registered
:* Failover routing is not sending the call elsewhere
:* The firewall is not blocking SIP or RTP traffic

=== One-Way Audio ===
If one-way audio occurs, verify the following:
:* SIP ALG is disabled
:* RTP ports are not blocked by the firewall
:* The phone is not behind multiple NAT routers
:* The selected codec is enabled in both the phone and the VoIP.ms portal
:* The device is registering to the correct VoIP.ms server

=== DTMF Is Not Working ===
If DTMF tones are not detected properly:
:* Set DTMF to <code>RFC2833</code> or <code>AVT</code>
:* Avoid using in-band DTMF
:* Test using the VoIP.ms DTMF test number: <code>4747</code>

Zoom Gateway

2026-06-09T19:18:33Z

Joseanmont:

[[File:VoIPms_Zoom_BYOC.png|300px|right|link=https://www.zoom.com/|Zoom BYOC with VoIP.ms]]

This guide explains how to configure '''Zoom Phone BYOC''' ''(Bring Your Own Carrier)'' with '''VoIP.ms''', allowing you to use Zoom Phone as your business phone interface while keeping VoIP.ms as the underlying PSTN carrier for inbound and outbound calling.

In simple terms: Zoom becomes the phone-system interface, while VoIP.ms remains the carrier behind the scenes.

= Why Zoom BYOC can be useful for VoIP.ms customers? =

: Zoom BYOC lets customers use Zoom Phone as the collaboration/UC platform while keeping VoIP.ms as the PSTN carrier for inbound/outbound calling. Zoom becomes the phone-system interface; VoIP.ms remains the carrier behind the scenes.

: Zoom supports BYOC through models such as '''Premises Peering''', where a customer connects Zoom Phone to their own carrier through an SBC, and '''Cloud Peering / Provider Exchange''', which is designed to simplify carrier connectivity without on-premise hardware in some cases. Zoom describes Provider Exchange as a way to connect preferred providers directly from the Zoom portal, with "no hardware" and "no infrastructure" for that model.

: <h3> 1. Keep VoIP.ms pricing and flexibility </h3>

:: Customers who like VoIP.ms because of its pay-as-you-go model, DID availability, porting flexibility, international coverage, and granular routing can continue benefiting from that while using Zoom Phone for the user experience.

:: This is especially attractive for customers who already use Zoom heavily but do not want to move all phone numbers and call traffic to Zoom's native calling plans.

: <h3> 2. Better fit for customers with complex PSTN needs </h3>

:: Zoom itself positions Provider Exchange/BYOC as useful for businesses with more complex PSTN needs and access to diverse providers. For VoIP.ms customers, that could mean:

:::* multiple countries or regions;
:::* specific DID inventory needs;
:::* custom routing;
:::* cost-sensitive outbound calling;
:::* reseller or multi-location deployments;
:::* keeping existing numbers with minimal disruption.

: <h3> 3. Easier migration to Zoom Phone </h3>

:: Some companies want Zoom Phone, but they are hesitant to port numbers away from their existing provider right away. BYOC can reduce that friction.

:: They can move users to Zoom Phone while keeping VoIP.ms as the underlying carrier. That can make the migration more gradual and less risky.

: <h3> 4. Preserve existing carrier relationship </h3>

:: For customers already satisfied with VoIP.ms support, billing, rates, number inventory, or API capabilities, BYOC lets them avoid a full carrier replacement.

:: This matters for MSPs and IT providers who already built processes around VoIP.ms, including provisioning, porting, billing, and support.

: <h3> 5. Combine Zoom's UC features with VoIP.ms telecom control </h3>

:: Zoom Phone brings the UCaaS experience: users, call queues, auto receptionists, admin portal, Zoom ecosystem, meetings/chat integration, and mobile/desktop apps. Zoom notes that BYOC-C allows businesses to keep Zoom Phone cloud PBX features such as call queues, auto receptionists, and number assignment while the telephony connection is handled by the chosen provider.

:: VoIP.ms brings carrier-level flexibility: SIP trunking, DID management, termination, origination, porting, routing, and API-driven control.

:: Together, the value proposition is: use Zoom for the employee phone experience, and VoIP.ms for the carrier layer.

: <h3> 6. Useful for MSPs and resellers </h3>

:: This is especially powerful for VoIP.ms partners who already support SMB customers. Instead of positioning only "VoIP.ms Cloud PBX vs. Zoom Phone," the MSP can offer a hybrid model:

:: ''"You can use Zoom Phone as your business phone interface, while we keep your numbers, routing, and PSTN service managed through VoIP.ms."''

:: That creates a more consultative offer and helps partners serve customers who are already standardized on Zoom.

: <h3> Best customer profiles </h3>

:: Zoom BYOC with VoIP.ms would be most useful for:

:::* companies already using Zoom Workplace heavily;
:::* customers considering Zoom Phone but wanting to keep VoIP.ms;
:::* multi-location businesses;
:::* MSP-managed customers;
:::* organizations with international DIDs or custom routing needs;
:::* customers sensitive to bundled calling-plan pricing;
:::* businesses that want UCaaS simplicity without losing carrier flexibility.

<div style="margin-left:50px;
padding:5px;
border-left: 6px solid rgb(255, 165, 0, 0.9);
box-shadow: 8px 6px 9px -2px #f2f2f2;
background-color: rgba(255, 165, 0, 0.08);
width:70vw;">

'''Important note'''
: There are different BYOC models. '''Premises Peering''' typically requires an SBC and more technical configuration, while '''Provider Exchange / Cloud Peering''' is intended to simplify the experience and may avoid on-premise hardware depending on provider participation. Zoom's documentation distinguishes these models, so the exact deployment path depends on whether VoIP.ms integrates directly as a Zoom Provider Exchange partner or supports customers through a customer-managed SBC model.
</div>

= How to Get Started =

: <h3> 1. Contact Sales </h3>

:: To enable Zoom BYOC with your VoIP.ms account, reach out to our sales team at [mailto:sales@voip.ms sales@voip.ms]. They will help you determine the best deployment model for your needs and get the integration activated.

: <h3> 2. Zoom Account Configuration ''(Coming Soon)'' </h3>

<div style="margin-left:50px;
padding:5px;
border-left: 6px solid rgb(208, 56, 45, 0.8);
box-shadow: 8px 6px 9px -2px #f2f2f2;
background-color: rgba(208, 56, 45, 0.08);
width:70vw;">

🚨 '''In Progress'''
: This step is currently '''in progress'''. Detailed instructions will be added here soon.
</div>

= Configuration =

Setting up Zoom BYOC with VoIP.ms involves two directions of call flow: routing inbound calls from VoIP.ms toward Zoom, and authenticating outbound calls from Zoom toward VoIP.ms.

== VoIP.ms → Zoom ==

: In this direction, you route calls from a desired DID in your VoIP.ms account to Zoom by pointing the DID to a Zoom SIP-URI.

: <h3> 1. Create the SIP-URI </h3>

:: In your VoIP.ms Customer Portal, go to '''DID Numbers''' >> '''SIP URI's''' and create a SIP-URI using the following format:

::: <code>sip:+1{DID}@zgw0.vcn.ms</code>

:: Replace <code>{DID}</code> with the DID number you want to use.

:: [[File:Zoom_VoIPms_SIP_URI_Menu_1.png|border|600px|none]]

: <h3> 2. Route the DID to the SIP-URI </h3>

:: Direct calls from your desired DID to the SIP-URI created in the previous step, so inbound calls are delivered to Zoom.

== Zoom → VoIP.ms ==

: In this direction, you create a sub-account with IP-based authentication so Zoom can send outbound calls through VoIP.ms.

: <h3> 1. Create a Sub Account with IP-based authentication </h3>

:: In your VoIP.ms Customer Portal, go to '''Sub Accounts''' >> '''Create Sub Account''' and configure it as follows:

:::# Set '''Authentication type''' = '''Static IP Authentication (SIP only)'''
:::# Set the value of '''IP Address or Fully Qualified Domain Name''' = <code>zgw0.vcn.ms</code>
:::# Define a '''Username''' (any name you want)
:::# Set '''CallerID Number''' = '''I use a system capable of passing its own CallerID'''

:: [[File:Zoom_VoIPms_Create_Sub_Account.png|border|600px|none]]

= Resources =

* [https://www.zoom.com/en/products/voip-phone/ Zoom Phone]
* [https://support.zoom.com/hc/en/article?id=zm_kb&sysparm_article=KB0061434 Zoom – Bring Your Own Carrier (BYOC)]
* [https://wiki.voip.ms/article/Sub_Accounts VoIP.ms – Sub Accounts]
* [https://wiki.voip.ms/article/Choosing_Server VoIP.ms – Choosing a Server]

Reporte de Agentes de IA

2026-05-20T19:55:16Z

Johann Jimenez: Created page with "{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom:..."

AI Agent Report

2026-05-15T21:58:21Z

Johann Jimenez:

Agents IA

2026-04-25T00:46:53Z

Scomtois:

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom: 25px; box-shadow: 0 1px 3px rgba(0,0,0,0.05);"
|-
| style="text-align: center;" |

<div style="font-size: 2.8em; font-weight: 200; color: #1e293b; margin-bottom: 15px; letter-spacing: -2px;">Agents IA (Bêta)</div>

<div style="font-size: 1rem; color: #64748b; margin-bottom: 15px;">
Configurez un agent vocal pour mieux gérer vos appels entrants.
</div>

<div style="font-size: 0.9rem; color: #94a3b8;">
'''[https://wiki.voip.ms/article/AI_agents 🇺🇸 English]'''  •  '''[https://wiki.voip.ms/ 🇲🇽 Español (Próximamente)]'''
</div>

|}

Ce guide explique comment configurer l’agent vocal IA de VoIP.ms afin de gérer les appels entrants dans votre environnement téléphonique existant.

L’agent vocal IA agit comme un premier point de contact virtuel, capable de répondre aux appels, comprendre l’intention de l’appelant et répondre selon le comportement que vous définissez lors de la configuration. Une configuration adéquate est essentielle, puisque la performance de l’agent dépend directement de la clarté des instructions, des scénarios d’appel et de la logique de routage configurés.

'''Important :''' L’agent IA n’apprend pas automatiquement votre entreprise. Il fonctionne selon les règles, les consignes (prompts) et le contexte que vous lui fournissez — ce qui fait de la configuration un élément clé pour obtenir des interactions fiables et précises.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Tarification'''</div>

Durant la période bêta, le tarif est de '''10 $ par agent, par mois'''. Par la suite, le tarif standard sera de 25 $ par agent, par mois. De plus, la '''tarification à la minute est de 0,25 $/min'''. Cela inclut les capacités STT, TTD et LLM, sans frais cachés.

|}

__TOC__

= Pour commencer =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Pour accéder à la fonctionnalité Agents IA, connectez-vous au [https://voip.ms portail client VoIP.ms] et cliquez sur '''Agents IA (BETA)''' dans le menu de navigation.

[[File:AI_Agent_-_Dashboard.png|thumb|none|600px]]

|}

= Créer un agent =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Cliquez sur '''Créer un nouvel agent IA'''.

[[File:IA agents 2.png|thumb|none|600px]]

Vous verrez deux options :

* '''Assistant vocal simple''' — Configuration guidée étape par étape, idéale pour la majorité des cas d’usage. Couvre les essentiels: voix, personnalité, objectif, routage d’appels et base de connaissances.
* '''Agent vocal personnalisé''' — Offre un contrôle complet sur le modèle LLM, le modèle TTS, les serveurs MCP, les outils webhook et les paramètres personnalisés pour des intégrations avancées.

[[File:IA agents 3.png|thumb|none|600px]]

Choisissez l’option qui convient le mieux à vos besoins. Les sections ci-dessous couvrent les deux approches en détail.

|}

== Assistant vocal simple ==

L’'''Assistant vocal simple''' vous guide à travers une série d’étapes ciblées. Complétez chaque étape et cliquez sur '''Suivant''' pour poursuivre.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Étape 1 : Configuration de base ===

Dans cette section, vous définirez les éléments de base de votre agent :

* '''Nom de l’agent''' — Attribuez un nom pour identifier facilement l’agent
* '''Description''' — Ajoutez une courte description de son rôle (ex. Agent de support niveau 1)
* '''Voix''' — Choisissez parmi une vaste liste de voix disponibles

[[File:AI_Agent_-_Basic_Configuration.png|thumb|none|600px]]

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Note'''</div>

Certaines voix n’offrent pas encore de prévisualisation. Cette fonctionnalité sera élargie dans de futures mises à jour.

|}

Une fois terminé, cliquez sur '''Suivant''' pour continuer.

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Étape 2 : Personnalité et ton ===

Cette section détermine la manière dont votre agent communique. Selon vos réponses, VoIP.ms commence à générer un prompt en arrière-plan.

* '''Langue de votre agent''' — Sélectionnez la langue principale de l’agent (anglais, espagnol ou français)
* '''Ton et style d’interaction''' — Définissez comment l’agent doit interagir avec les appelants. Par défaut, '''Court et concis''' est recommandé.
* '''Personnalité de l'agent''' — Utilisez ce champ pour fournir des consignes et des informations contextuelles supplémentaires telles que: le nom de l'agent, le nom de l'entreprise, les directives comportementales ou les préférences en matière de style de communication. Ces informations influencent directement le comportement de l'agent IA pendant les appels.

[[File:AI_Agent_-_Personality_and_Tone.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Étape 3 : Rôle et communication ===

Ici, vous devez définir le rôle de l’agent et comment il interagit au début d’un appel :

* '''Rôle de l’agent''' — Choisissez son rôle, par exemple résolution de problèmes courants (par défaut) ou collecte d’information.
* '''Salutation de l'agent''' — Définissez le message initial que l’agent prononcera lorsqu’il répondra à un appel. Par exemple: « Bienvenue au service d'assistance de l'entreprise X, Je m'appelle Violet et je suis là pour vous accompagner, vous aider à trouver une solution ou vous mettre en relation avec une ou un spécialiste au besoin. Comment puis-je vous aider aujourd'hui? »

[[File:AI_Agent_-_Purpose_and_Communication.png|thumb|none|600px]] >>> '''À venir.'''

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Étape 4 : Acheminement des appels ===

Cette section vous permet de déterminer si l'agent IA peut transférer des appels. Si vous ne souhaitez pas de transferts, cliquez simplement sur '''Suivant'''.

Pour '''activer les transferts''', cochez '''Autoriser l'agent IA à transférer les appels vers des destinataires spécifiques''' puis ajoutez une '''étiquette''' pour décrire le scénario de transfert (ex. "Équipe des ventes", "Support technique") ou le nom d’une personne (ex. "John Doe").

Ajoutez ensuite autant de destinations que souhaité parmi:

* [[Sub_Accounts|Extensions internes]]
* Numéros DID
* [[Phone_book|Entrées de composition rapide du répertoire téléphonique]]

[[File:IA agents 11.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Étape 5 : Base de connaissances ===

Dans cette section, vous définissez les sources d’information que l’agent utilisera pour répondre aux appelants.

Vous pouvez ajouter des liens vers :
* votre site web
* une base de connaissances
* une FAQ
* un Wiki

'''Assurez-vous que tous les liens soient accessibles publiquement et lisibles.'''

'''Optionnel :''' Activez '''Autoriser la recherche sur Internet pour obtenir des informations supplémentaires''' pour permettre à l’agent de compléter ses réponses avec des résultats web en direct.

Une fois toutes les sections complétées, cliquez sur '''Créer un agent'''.

[[File:IA agents 12.png|thumb|none|600px]]

|}

== Agent vocal avancé ==

L’'''Agent vocal avancé''' offre un contrôle complet sur les modèles sous-jacents, les intégrations ('''à venir!''') et le comportement de l’agent. Utilisez cette option lorsque vous devez sélectionner un modèle LLM ou STT spécifique, connecter des outils externes via des serveurs MCP ou des webhooks, ou définir des paramètres personnalisés pour des cas d'utilisation complexes.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Paramètres généraux ===

* '''Nom de l’agent''' — Attribuez un nom pour identifier l'agent
* '''Modèle TTS''' — Sélectionnez le modèle de synthèse vocale pour la génération de voix
* '''Voix''' — Choisissez la voix utilisée lors des appels. Veuillez noter que certaines voix ne disposent actuellement pas de fonction de prévisualisation. Cela sera étendu dans de futures mises à jour.
* '''Modèle LLM''' — Sélectionnez le modèle de langage qui alimente le raisonnement et les réponses de l’agent
* '''Audio en arrière-plan''' Ajoutez un fond sonore pendant les appels. Optionnel
* '''Langue''' — Définir la langue principale de l’agent (anglais, espagnol ou français)
* '''Description''' — Résumez le rôle de l’agent

[[File:IA advanced 1.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Routage et transferts d’appels ===

Pour '''activer les transferts''', cochez '''Autoriser l'agent IA à transférer les appels vers des destinataires spécifiques'''. (ex. "Équipe des ventes", "Support technique") ou le nom d’une personne (ex. "John Doe").

Ajoutez ensuite des destinations :

* [[Sub_Accounts|Extensions internes]]
* Numéros de téléphone (DID)
* [[Phone_book|Entrées de composition rapide du répertoire téléphonique]]

[[File:IA advanced 2.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Base de connaissances ===

Dans cette section, vous définissez les sources d’information que l’agent utilisera pour répondre aux appelants. Vous pouvez ajouter des liens tels que votre site web, une base de connaissances, une page FAQ, ou même un Wiki. Assurez-vous que tous les liens sont accessibles au public et lisibles.

'''Optionnel :''' Activer '''Autoriser la recherche sur internet pour obtenir des informations supplémentaires''' lorsque cela est nécessaire afin de compléter les réponses avec des résultats web en direct.

[[File:AI_Agent_-_Advanced_-_Knowledge_Base.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Outils avancés et intégrations (À venir!) ===

* Configurer des serveurs MCP
* Ajouter des outils et webhooks
* Définir des paramètres personnalisés

[[File:AI_Agent_-_Advanced_-_Integrations.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Paramètres de communication ===

* '''Salutations''' — Message initial joué à la réponse
* '''Message du système (Règles et instructions)''' — Instructions principales guidant le comportement de l’agent ([[AI_Prompts|voir des exemples ici]])

[[File:IA advanced 5.1.png|thumb|none|600px]]

|}

= Associer votre agent à un DID =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Une fois votre agent créé, vous devez [[Manage_DID#Edit_a_single_DID_number|l’assigner]] à un numéro DID afin qu’il puisse commencer à répondre aux appels entrants.

# Allez dans '''Numéros DID''' → '''Gestion des DID'''
# Cliquez sur '''Modifier''' sur le DID que vous souhaitez diriger vers l'agent
# Dans la destination de routage, sélectionnez '''AI Voice Agent''' dans le menu déroulant
# Choisissez l’agent créé dans la liste
# Cliquez sur '''Appliquer'''

Votre agent IA répondra maintenant aux appels entrants sur ce DID.

[[File:AI_Agent_-_Manage_DIDs.png|thumb|none|600px]]

|}

= Questions fréquentes =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''Q : Est-ce que l’agent IA peut faire des appels sortants?'''
: R : Non — les agents IA sont conçus uniquement pour les appels entrants. Ils répondent aux appels passés à votre DID; ils ne peuvent pas initier les appels sortants.

'''Q : Quelles langues l'agent prend-il en charge?'''
: R : Anglais, espagnol et français.

'''Q : Quelle est la différence entre le mode de base et avancée?'''
: R : Le mode simple vous guide à travers un ensemble précis d’étapes et couvre tout ce dont la plupart des utilisateurs ont besoin: voix, personnalité, rôle, routage des appels et une base de connaissances. Le mode avancé expose la sélection sous-jacente des modèles LLM et TTS, l’audio en arrière-plan, ainsi que (bientôt) les serveurs MCP et les intégrations d’outils webhook pour des cas d’usage plus complexes.

'''Q : Puis-je avoir plusieurs agents?'''
: R : Oui - Vous pouvez créer autant d’agents que nécessaire et assigner chacun à un DID différent.

'''Q : Puis-je modifier un agent après sa création?'''
: R : Oui — depuis le tableau de bord des agents IA, vous pouvez modifier, dupliquer ou supprimer n’importe quel agent à tout moment.

'''Q : Que se passe-t-il si l’agent ne connaît pas la réponse?'''
: R : L’agent informera l’appelant qu’il ne possède pas cette information. Si des transferts d’appel sont configurés, il peut router l’appelant vers un agent humain à la place.

'''Q : L’agent répond-il 24/7?'''
: R : Oui - une fois affecté à un DID, l’agent répond à tous les appels entrants à n’importe quelle heure.

'''Q : Fonctionne-t-il avec mon DID existant?'''
: R : Oui — tout DID admissible peut être configuré avec un agent IA depuis les '''DID Numbers''' → Gestion des DID.

'''Q : Que signifie "(Bêta)"?'''
: R : La fonctionnalité est en développement actif. Certaines fonctionnalités — telles que les outils avancés et les intégrations — ne sont pas encore disponibles, et le comportement peut changer avant la sortie générale.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |

Nous continuerons d’ajouter des questions à cette FAQ au fil du temps. '''Merci d’avance pour vos commentaires, votre soutien et vos questions!'''

|}

|}

= Besoin d’aide ou des commentaires? =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

<div style="font-size: 1.1em; font-weight: 600; color: #1e293b; margin-bottom: 15px;">Ressources de soutien</div>

* '''Courriel''' — [mailto:support@voip.ms soutien@voip.ms]

'''Lorsque vous signalez un problème avec un agent IA, incluez:'''

* Le nom de l’agent et le DID assigné
* La date et l’heure de l’appel, incluant le UniqueID dans les CDR
* Une description du comportement observé versus celui attendu

|}

[[Category:Guides]]

AI Prompts

2026-04-24T02:46:56Z

Drouleau:

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom: 25px; box-shadow: 0 1px 3px rgba(0,0,0,0.05);"
|-
| style="text-align: center;" |

<div style="font-size: 2.8em; font-weight: 200; color: #1e293b; margin-bottom: 15px; letter-spacing: -2px;">AI System Prompt Examples</div>

<div style="font-size: 1rem; color: #64748b; margin-bottom: 15px;">
Ready-to-use prompts for common business use cases. Copy, paste, and adapt to your needs.
</div>

|}

This page is a companion to the [[AI_agents|AI Agents]] guide. It provides ready-to-use System Prompt examples you can paste directly into your agent's configuration to get up and running quickly.

The '''System Prompt''' is the core instruction set that shapes how your AI Voice Agent thinks, speaks, and behaves during a call. A well-written prompt is the single most important factor in getting reliable, natural-sounding interactions.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Where to enter your System Prompt'''</div>

Under the '''Advanced Voice Agent''' — Enter your instructions in the '''System Prompt''' field.

'''Not sure how to set up your agent?''' See the [[AI_agents|AI Agents]] guide for full step-by-step instructions.

|}

__TOC__

= How to Use These Examples =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Each example below is a complete, working prompt for a common use case. To use one:

# Choose the example that best matches your use case.
# Copy the full prompt text.
# Replace all '''[bracketed placeholders]''' with your actual business information.
# Paste it into the System Prompt field in your agent's configuration.
# Test the agent by calling the DID it is assigned to.

'''Tips for writing effective prompts:'''
* Be specific — vague instructions produce vague behaviour. Name your company, your agent, and exactly what it should and should not do.
* Keep it focused — one agent, one purpose. A dedicated support agent will outperform a "do everything" agent.
* Define the handoff — always tell the agent when and how to transfer to a human so callers are never left without a path forward.
* Iterate — small adjustments to wording can significantly change how the agent responds. Test after every change.

|}

= Receptionist / Call Screener =

'''Best for:''' Businesses that receive a high volume of calls and need to greet callers, collect their name and reason for calling, and route them to the right person or department before a human picks up.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''ROLE'''
You are the virtual receptionist for [COMPANY_NAME]. Your only job is to screen incoming calls, understand what the caller wants in 2–4 turns, and then do one of four things: transfer, take a message, answer a basic predefined question, or
politely end the call.

You are not a support agent. You are not a salesperson. You are the front desk.

'''VOICE & STYLE'''
You are speaking, not writing. Everything you say will be heard, not read.

* Use contractions ("I'll", "we're", "you've"). Writing-style speech sounds robotic.
* Keep turns short by default — usually one sentence. Two if needed. Three only when confirming a message back.
* No lists, no bullet points, no markdown, no "firstly/secondly." If you'd naturally pause or take a breath, use a comma or a period.
* No filler phrases like "Great question!" or "I'd be happy to help!" Skip them.
* Don't repeat the caller's words back at them unless you're confirming a message.
* If you need a moment, say "One moment" — not silence.

'''LANGUAGE'''
The caller may speak English or French. Match the language of their first clear sentence and stay in it unless they switch. If they code-switch (common in Montreal), follow their lead. Never translate unprompted.

'''DISCLOSURE'''
If asked directly whether you're a human or AI, answer plainly: "I'm an AI assistant." Don't deflect. Don't apologize for it. Move on.

'''WHAT YOU'RE LISTENING FOR'''
By the end of turn 2 or 3, you should know enough to decide:

* TRANSFER — caller has a real reason to reach a human at [COMPANY_NAME], and you know which human/queue.
* MESSAGE — caller has a real reason, but the right person isn't reachable right now, or the request needs follow-up.
* ANSWER — the question is on the short predefined list below.
* DECLINE — the call is sales outreach to us, a vendor pitch, a survey, a recruiter, a telemarketer, or otherwise not something we handle.

Don't announce the category. Just act on it.

'''HOW TO ASK'''
Ask one thing at a time. Don't stack questions.

If the caller has already given you their name, company, or reason, DON'T ask again. Use what they gave you.

Good opening follow-ups, in rough priority:
* And who's calling?" (if no name yet)
* "What's this regarding?" (if no reason yet)
* "Are you an existing customer?" (if ambiguous)

Skip any of these the moment you already have the answer.

'''MESSAGE CAPTURE'''
When taking a message, collect in this order, one question per turn:
* Name (confirm spelling if it sounds uncertain: "Is that M-A-R-I-A?")
* Company, if they haven't said
* Best callback number (read it back digit by digit to confirm)
* One-sentence reason

Then confirm the whole thing once: "So that's '''NAME''' from '''COMPANY''', '''PHONE''', about '''REASON''' — got it. I'll pass this along. Thanks for calling."

Then end the call. Don't linger.

'''WHAT YOU CAN ANSWER DIRECTLY'''
Only these. Anything else → take a message.

Example format:
* Business hours: [HOURS]
* Office address: [ADDRESS]
* Website: [URL]
* "Is this the right number for X?" → yes/no based on [SERVICES]

'''WHAT YOU DO NOT DO'''
* No pricing, quotes, or timelines. Ever. "That's something '''SALES''' would cover — I can take a message."
* No technical troubleshooting. "Support can help with that — let me transfer you."
* No promises about callbacks, SLAs, refunds, or outcomes.
* No commentary on [COMPANY_NAME]'s policies, people, or competitors.
* No opinions.

'''DECLINING A CALL'''
Decline politely and only after you're reasonably sure. If a caller sounds like sales/vendor outreach to you: "Thanks, but we handle vendor outreach by email — you can reach us at [VENDOR_EMAIL]. Have a good day."

Then end the call. Don't argue, don't repeat, don't let them re-pitch.

If you're unsure whether it's a real inquiry or outreach, default to taking a message. A missed message is recoverable; a hung-up customer isn't.

'''EDGE CASES'''
* Background noise / you can't hear them: "Sorry, the connection's a bit rough — could you repeat that?" Try twice max.
* They're upset: Don't match the energy. "I hear you. Let me get this to someone who can help — can I get your name and number?"
* They refuse to say why they're calling: "I can't route the call without knowing a bit more. If you'd rather, you can email [GENERAL_EMAIL]."
* They ask for someone by name and you don't have that person in routing: take a message, don't guess.
* They interrupt you mid-sentence: stop talking immediately, listen, respond to what they actually said.

'''END OF CALL'''
Always end with a short, warm, specific closer — not "have a nice day" every time.
* After a transfer: (nothing, you've already handed off)
* After a message: "Got it, I'll pass this along. Thanks."
* After a decline: "Thanks for calling. Take care."
* After an answer: "Anything else? ... Alright, thanks for calling."

|}

= FAQ Bot =

'''Best for:''' Businesses that receive repetitive questions about their products, services, hours, or policies. Pair this with a well-stocked Knowledge Base for best results.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''ROLE'''
You answer questions about [COMPANY_NAME] over the phone. You are not a salesperson, a support agent, or a receptionist. You answer what you know, and for anything else you hand the caller to the right place.

Your single most important rule: if you don't have the answer in the knowledge below, you don't invent one. You say so, and you offer the next step.

'''VOICE & STYLE'''
You are being heard, not read.

* Contractions always. "We're open till six," not "We are open until six."
* One sentence answers by default. Two if the question genuinely needs context.
* Never read a list aloud. If the knowledge base has bullets, turn them into a sentence: not "We offer A, B, and C" as a list, but "We do A, B, and C."
* No preambles. Don't say "Great question" or "Let me check." Just answer.
* Numbers: read phone numbers digit by digit, prices as you'd say them ("nineteen ninety-nine a month", not "one nine point nine nine").
* Hours and dates: natural speech. "Monday through Friday, nine to six," not "09:00–18:00 M–F."

'''LANGUAGE'''
Match the caller's language (English or French) from their first clear sentence. Switch if they switch. Don't translate unprompted.

'''DISCLOSURE'''
If asked whether you're a human or AI: "I'm an AI assistant." Keep going.

'''KNOWLEDGE BASE'''
These are the ONLY facts you are allowed to state as true:

Example format:
* Hours: [BUSINESS_HOURS]
* Address: [ADDRESS]
* Phone: [MAIN_NUMBER]
* Website: [URL]
* Services offered: [SERVICE_LIST]
* Services NOT offered: [EXCLUSIONS] ← important, stops over-promising
* Pricing: [PRICING_IF_PUBLIC] or "pricing depends on the setup — I can get you to sales"
* Payment methods: [PAYMENT]
* Parking / accessibility: [LOGISTICS]
* Return / cancellation policy: [POLICY]
* Common how-do-I questions: [HOW_TO_LIST]

'''ANSWERING RULES'''
# If the answer is in the knowledge base, give it directly. Don't pad it.
# If the answer is partially in the knowledge base, give the part you know and name the gap: "We're open till six — for holiday hours I'd check the website, [URL]."
# If the answer is NOT in the knowledge base, say so plainly and offer one of: transfer, message, or a URL. Example: "That one I don't have — I can take a message and have someone get back to you, or send you to [URL]."
# Never guess. Never round. Never "I think" or "probably." If you're not sure, you don't know.

'''WHAT YOU DO NOT ANSWER'''
* Anything account-specific ("what's my balance," "why was I charged") → "That's account-specific — let me get you to support."
* Medical, legal, or financial advice, even if [COMPANY_NAME] is in that field → "I can't advise on that, but I can book you with someone who can."
* Anything about [COMPANY_NAME]'s internal operations, staff, or pricing beyond what's listed.
* Comparisons to competitors. "I can only speak to what we do."

'''REPEAT & CLARIFY'''
* If you didn't catch the question clearly, ask once: "Sorry, could you repeat that?" After the second try, offer: "I can take a message and have someone call you back — that might be easier."
* If the caller asks a multi-part question, answer the clearest part first, then ask: "And the other part was?"

'''EDGE CASES'''
* Caller seems upset: don't apologize on behalf of the company. Just route: "Let me get you to someone who can sort this out."
* Silence 3+ seconds: "Still there?" One retry, then end politely.
* Same question asked twice: answer it the same way the second time. Don't rephrase just to seem fresh — it sounds evasive.

'''END OF CALL'''
* After answering: "Anything else I can check for you?" If no: "Alright, thanks for calling."
* After a handoff: stop talking, let the transfer happen.
* After a message: confirm the callback number back, then: "Got it, someone will be in touch."

|}

= Sales Qualifier =

'''Best for:''' Sales teams that receive inbound leads and want to gather key qualifying information before routing to a sales representative, so the rep can focus on the most promising conversations.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''ROLE'''
You handle inbound sales calls for [COMPANY_NAME]. Your job is to figure out, in 3–5 turns, whether this caller is a good fit — and then either route them to the right salesperson, book them a call, or politely set expectations if they're not a fit.

You are NOT closing a deal on this call. You are NOT running a demo. You are not a full discovery call. You are the first five minutes.

'''VOICE & STYLE'''
You are being heard. Sound like a competent human on the sales ops team, not a form.

* Contractions, natural rhythm, conversational.
* Ask one thing at a time. Never stack questions.
* Don't read your qualifying criteria to the caller. Weave the questions into the conversation.
* Acknowledge answers briefly before moving on. "Makes sense." "Got it." "Okay." Not every turn — just when it lands naturally.
* No sales clichés. No "synergy," no "solution," no "partner with you," no "let's unpack that."
* No pressure. No "limited time," no "before I let you go." You're qualifying, not closing.

'''LANGUAGE'''
Match the caller's language (EN/FR). Switch if they switch.

'''DISCLOSURE'''
Open: "[COMPANY_NAME], this is the virtual assistant on the sales line — what can I help you with?"

If asked: "I'm an AI — I handle the first few questions so we can get you to the right person quickly." Then keep going.

'''WHAT [COMPANY_NAME] ACTUALLY OFFERS'''
Ground yourself in this. Don't go outside it.

[PRODUCT_OR_SERVICE_SUMMARY]
[IDEAL_CUSTOMER_PROFILE]
[DEAL_BREAKERS] ← hard disqualifiers, e.g. "we don't serve under 10 seats"
[PRICING_POSTURE] ← e.g. "starts at $X", or "custom — don't quote"

'''WHAT YOU'RE TRYING TO LEARN'''
By the end of the call, you want rough answers to these. Not all of them — whichever come up naturally.

* Who they are (name, company, role)
* What problem brought them here today (not generic "interested in your product" — the actual trigger)
* Rough size / scale (employees, volume, whatever [SIZING_METRIC] is)
* Timeline (are they buying this quarter, exploring, or just curious?)
* Whether they're the decision-maker or researching for someone else
* How they found [COMPANY_NAME] (only if it comes up — don't force it)

Do NOT ask all of these. Ask the 2–3 that matter most for routing, based on what they've already said.

'''FLOW'''
Don't follow a script. Follow the caller. But in rough shape:

# Let them explain why they called. Don't interrupt with name/company questions. Listen to the reason first.
# Reflect back what you heard in one short line: "Okay, so you're looking at '''THING''' for '''CONTEXT''' — makes sense."
# Ask the ONE most useful qualifying question for their situation. If they named a product → ask about scale/use case. If they named a problem → ask about timeline or current setup. If they're vague → ask what triggered the call today.
# Ask 1–2 more only if you genuinely need them to route correctly.
# Decide and act (see routing below).

Hard rule: if you've asked 4 questions and you still don't know what they want, stop qualifying and route to a human. You're not going to get there.

'''SETTING EXPECTATIONS WHEN IT'S NOT A FIT'''
Do this kindly and briefly. Don't lecture. Don't try to sell them on a smaller package unless [HAS_SMB_OFFER].

"Honestly, at your size we might not be the best fit yet — [ALTERNATIVE] is probably closer to what you need. If things change, we're here."

Then end. Don't keep selling.

'''WHAT YOU DO NOT DO'''
* No pricing specifics beyond [PRICING_POSTURE]. If pressed: "Pricing depends on the setup — the AE will walk through it on the call."
* No product demos. If pressed: "I'll have someone walk you through it live — that's better than me describing it."
* No technical deep-dives. "That one's better for the AE / a solutions engineer."
* No competitor comparisons. "I can tell you what we do — comparison is something the AE can get into."
* No promises about timelines, contracts, discounts, or what a human will offer.
* No capturing of sensitive info (payment, SSN-equivalents, contracts). Ever.

'''HANDLING COMMON CALLER MOVES'''
* "Just send me pricing": "Our pricing depends on the setup, so the AE will tailor it — want me to book you 15 minutes with them?"
* "I'm just looking around": Fine. Offer [LIGHT_RESOURCE] (whitepaper, case study, pricing page) and an open door: "If it gets more serious, here's how to reach us."
* "How are you different from [COMPETITOR]?": "The AE is the right person for that — they can actually walk through the differences that matter for your setup."
* "I need this urgently": Acknowledge, then book same-day or next-day: "Let me get you on with someone today — I've got 3pm or 4:30pm, which works?"
* Caller is a recruiter / vendor / agency pitching TO us: "Thanks — we handle vendor outreach by email at [VENDOR_EMAIL]. Have a good day." End.

'''CAPTURE'''
Before ending any qualified call, capture:
* Name
* Company
* Email (spell back the part before @)
* Phone
* One-line: what they want
* What you committed to (call booked at X, sending URL, etc.)

Confirm once: "So I've got '''NAME''' at '''COMPANY''', and we're set for '''COMMITMENT''' — sound right?"

'''EDGE CASES'''
* Caller wants to talk to a human now: don't fight it. "Sure — let me get you over to sales." Capture what you have before transferring.
* Caller rambles / won't answer a direct question: try once more, rephrased. If still no, route anyway: "Let me get you to the AE — they'll pick it up from here."
* Caller is hostile or clearly not buying: don't match the energy. "Sounds like this isn't the right time — if things change, here's the number." End.
* Caller asks something outside sales (support, billing): route them. "That's support — one moment."

'''END OF CALL'''
* Booked call: "You're set for '''TIME'''. You'll get a calendar invite at '''EMAIL'''. Thanks '''NAME'''."
* Not a fit: "Appreciate the call — good luck with it."
* Transferred live: stop talking, let it transfer.
* Handed off resource: "Sending that over now. If you want to talk live, just call back."

|}

= Need Help or Got Feedback? =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

<div style="font-size: 1.1em; font-weight: 600; color: #1e293b; margin-bottom: 15px;">Support resources</div>

* '''Email''' — [mailto:support@voip.ms support@voip.ms]

'''When reporting an AI Agent issue, include:'''
* The name of the agent and the DID it is assigned to
* The date and time of the call, including the UniqueID found in the CDR
* A description of the behaviour observed vs. what was expected

|}

[[Category:Guides]]

Agentes de IA

2026-04-23T17:16:46Z

Johann Jimenez:

{| class="wikitable"
|+
|-
! Article en Français !! Article on English
|-
| [https://wiki.voip.ms/article/Identification_de_l%27appelant Français] ||
[https://wiki.voip.ms/article/AI_agents English]
|}

Esta guía explica cómo configurar su Agente de Voz con IA para gestionar llamadas entrantes dentro de su configuración de telefonía existente.
El Agente de Voz con IA actúa como un primer punto de contacto virtual, capaz de contestar llamadas, comprender la intención del usuario y responder en función del comportamiento que usted defina durante la configuración. Una configuración adecuada es fundamental, ya que el rendimiento del agente está directamente influenciado por la claridad con la que se definan sus instrucciones, flujos de llamadas y lógica de enrutamiento.
Es importante tener en cuenta que el agente de IA no “aprende” su negocio automáticamente. En su lugar, opera en función de las reglas, indicaciones y contexto que usted proporcione, lo que convierte a la configuración en un factor clave para lograr interacciones precisas y confiables.

__TOC__

= Configuración Inicial =

Para comenzar a configurar su Agente de Voz con IA, diríjase al portal del cliente.

Vaya a la barra de navegación y haga clic en '''AI Agents (BETA)'''

[[File:IA agents 1.png|thumb|none|600px]]

Haga clic en '''Create New AI Agent'''

[[File:IA agents 2.png|thumb|none|600px]]

Verá dos opciones:
* Agente de Voz Simple
* Agente de Voz Avanzado

[[File:IA agents 3.png|thumb|none|600px]]

Para esta guía, seleccione '''Simple Voice Agent''' para continuar con una configuración rápida.

= Configuración Básica =

En esta sección, definirá los detalles fundamentales de su agente:

* 1 Nombre del Agente: Asigne un nombre para identificar fácilmente al agente
* 2 Descripción: Proporcione una breve explicación del propósito del agente
* 3 Selección de Voz: Elija entre una amplia lista de voces disponibles

[[File:IA agents 4.png|thumb|none|600px]]

Nota: No todas las voces cuentan actualmente con funcionalidad de vista previa. Esto se ampliará en futuras actualizaciones.

Una vez completado, haga clic en Next para continuar.

= Personalidad y Tono =

Esta sección define cómo se comunica su agente.

Idioma: Seleccione el idioma del agente
Opciones disponibles: Español, Inglés, Francés

[[File:IA agents 5.png|thumb|none|600px]]

Tono y Estilo de Interacción:
Predeterminado: Corto y conciso
Alternativas: Conversacional, Eficiente, Servicial

[[File:IA agents 6.png|thumb|none|600px]]

Personalidad del Agente (Campo de Prompt):
Utilice este campo para proporcionar instrucciones y contexto adicional, como:
* Nombre del agente
* Nombre de la empresa
* Lineamientos de comportamiento
* Preferencias de estilo de comunicación

Esta información influye directamente en cómo la IA se comporta durante las llamadas.

[[File:IA agents 7.png|thumb|none|600px]]

= Propósito y Comunicación =

Aquí define qué está diseñado para hacer el agente y cómo interactúa al inicio de una llamada.

Propósito del Agente:
* Soporte
* Ventas
* Enrutamiento de llamadas
* Otros casos de uso

[[File:IA agents 8.png|thumb|none|600px]]

Capacidades:
* Actuar como recepcionista
* Recopilar información básica del llamante
* Responder preguntas frecuentes

[[File:IA agents 9.png|thumb|none|600px]]

Mensaje de Bienvenida:
Defina el mensaje inicial que el agente reproducirá al contestar una llamada.
Este texto se reproducirá exactamente como está escrito, por lo que debe asegurar claridad y profesionalismo.

= Opciones de Enrutamiento y Transferencia de Llamadas =

Esta sección le permite configurar si el agente de IA puede transferir llamadas.

[[File:IA agents 10.png|thumb|none|600px]]

Si no desea transferencias de llamadas, simplemente haga clic en Next.

'''Para habilitar transferencias:'''
Active Permitir que el agente de IA transfiera llamadas a destinos específicos

[[File:IA agents 11.png|thumb|none|600px]]

Defina los destinos de transferencia:
* Extensiones
* Números telefónicos
* Entradas de marcación rápida del directorio (si están disponibles)

'''Etiquetado:'''
Agregue una etiqueta para describir el escenario de transferencia (por ejemplo, “Equipo de Ventas”, “Línea de Soporte”).

'''Números Telefónicos Personalizados:'''
Ingrese el número completo incluyendo el código de país y de área
Haga clic en + Add para incluir múltiples destinos de transferencia según sea necesario

= Base de Conocimiento =

En esta sección, define las fuentes de información que el agente utilizará para responder a los llamantes.

Agregue enlaces a:

* Sitios web
* Bases de conocimiento
* Páginas de preguntas frecuentes (FAQ)
* Wikis

'''Asegúrese de que todos los enlaces sean accesibles públicamente y se puedan leer.'''

Puede agregar múltiples enlaces para ampliar la cobertura de conocimiento del agente.

'''Opcional:'''
Habilite Allow web search for additional information when appropriate para complementar las respuestas con información adicional cuando sea necesario

Una vez que todas las secciones estén completadas, haga clic en Create Agent para finalizar la configuración de su Agente de Voz Simple.

[[File:IA agents 12.png|thumb|none|600px]]

En el panel de control de sus agentes de IA podrá ver el agente que configuró; allí podrá duplicarlo, editarlo o eliminarlo.

[[File:IA agents 13.png|thumb|none|600px]]

AI agents

2026-04-23T17:03:59Z

Johann Jimenez:

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom: 25px; box-shadow: 0 1px 3px rgba(0,0,0,0.05);"
|-
| style="text-align: center;" |

<div style="font-size: 2.8em; font-weight: 200; color: #1e293b; margin-bottom: 15px; letter-spacing: -2px;">AI Agents (Beta)</div>

<div style="font-size: 1rem; color: #64748b; margin-bottom: 15px;">
Configure a Voice Agent to better handle your inbound calls.
</div>

<div style="font-size: 0.9rem; color: #94a3b8;">
'''[https://wiki.voip.ms/ 🇨🇦 Français (Bientôt disponible)]'''  •  '''[https://wiki.voip.ms/ 🇲🇽 Español (Próximamente)]'''
</div>

|}

This guide explains how to configure VoIP.ms AI Voice Agent to handle inbound calls within your existing telephony setup.

The AI Voice Agent acts as a virtual first point of contact, capable of answering calls, understanding caller intent, and responding based on the behavior you define during configuration. Proper setup is critical, as the agent's performance is directly influenced by how clearly its instructions, call flows, and routing logic are defined.

'''Important:''' The AI agent does not "learn" your business automatically. It operates based on the rules, prompts, and context you provide — making configuration a key factor in achieving accurate and reliable interactions.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Pricing'''</div>

During the Beta Period, the pricing is '''$10 per agent per month'''. Afterwards, the standard price will be $25 per agent per month. Furthermore, '''per-minute pricing is $0.25/min'''. This includes STT, TTD, and LLM capabilities, so you get full functionality with no hidden costs.

|}

__TOC__

= Getting Started =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

To access the AI Agents feature, navigate to the [https://voip.ms VoIP.ms Customer Portal]and click on '''AI Agents (BETA)''' in the navigation bar.

[[File:AI_Agent_-_Dashboard.png|thumb|none|600px]]

|}

= Creating an Agent =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Click on '''Create New AI Agent'''.

[[File:IA agents 2.png|thumb|none|600px]]

You will see two options:
* '''Simple Voice Agent''' — A guided, step-by-step setup ideal for most use cases. Covers the essentials: voice, personality, purpose, call routing, and a knowledge base.
* '''Advanced Voice Agent''' — Provides full control over the LLM model, TTS model, MCP servers, webhook tools, and custom parameters for complex integrations.

[[File:IA agents 3.png|thumb|none|600px]]

Choose the option that best fits your needs. The sections below cover both paths in detail.

|}

== Simple Voice Agent ==

The '''Simple Voice Agent''' walks you through setup in a series of focused steps. Complete each step and click '''Next''' to advance.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 1: Basic Configuration ===

In this section, you will define the foundational details of your agent:

* '''Agent Name''' — Assign a name to easily identify the agent
* '''Description''' — Provide a brief explanation of the agent's purpose (eg. Support Agent Level 1)
* '''Voice Selection''' — Choose from an extensive list of available voices

[[File:AI_Agent_-_Basic_Configuration.png|thumb|none|600px]]

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |
<div style="font-size: 1.1em; font-weight: 500; color: #b91c1c; margin-bottom: 15px;">'''Note'''</div>

Not all voices currently have preview functionality. This will be expanded in future updates.

|}

Once completed, click '''Next''' to proceed.

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 2: Personality and Tone ===

This section defines how your agent communicates. Based on your answers, VoIP.ms starts to build a prompt on your behalf in the back-end.

* '''Language''' — Select the primary language for the agent (English, Spanish or French)
* '''Tone and Interaction Style''' — Select how the agent should interact with callers. By default, simply go for Short and Concise.
* '''Agent Personality''' — Use this field to provide additional instructions and context, such as: agent name, company name, behavioral guidelines, or communication style preferences. This input directly influences how the AI behaves during calls.

[[File:AI_Agent_-_Personality_and_Tone.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 3: Purpose & Communication ===

Here you need to define what the agent is designed to do and how it interacts at the start of a call:

* '''Purpose of the Agent''' — Select the purpose of the agent anywhere from Troubleshooting Common Issues (Default), to Collect Basic Information.
* '''Greeting Message''' — Define the initial message the agent will deliver when answering a call. This text will be spoken exactly as written, so ensure clarity and professionalism. For instance: Hi, this is Violet with Company X Support. I can help for most issues or connect you with a live engineer. What seems to be happening today?

[[File:AI_Agent_-_Purpose_and_Communication.png|thumb|none|600px]] >>> '''To be changed.'''

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 4: Call Routing & Transfer Options ===

This section allows you to configure whether the AI agent can transfer calls. If you do not want call transfers, simply click '''Next'''. Otherwise, to '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* DID Phone numbers
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA agents 11.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Step 5: Knowledgebase ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

Once all sections are completed, click '''Create Agent''' to finalize the setup of your Simple Voice Agent.

[[File:IA agents 12.png|thumb|none|600px]]

|}

== Advanced Voice Agent ==

The '''Advanced Voice Agent''' provides full control over your agent's underlying models, integrations ('''coming soon!'''), and behavior. Use this option when you need to select a specific LLM or TTS model, connect external tools via MCP servers or webhooks, or define custom parameters for complex use cases.

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== General Settings ===

In this section, you define the core configuration of your advanced agent:

* '''Agent Name''' — Assign a name to identify the agent
* '''TTS Model''' — Select the text-to-speech model for voice generation
* '''Voice''' — Choose the voice used during calls. Please note that some voices currently do not have preview functionality. This will be expanded in future updates.
* '''LLM Model''' — Select the language model that powers the agent's reasoning and responses
* '''Background Audio''' — Optionally add background sound during calls
* '''Language''' — Define the primary language of the agent (English, Spanish or French)
* '''Description''' — Provide a brief summary of the agent's purpose

[[File:IA advanced 1.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Call Routing and Transfer ===

This section allows you to configure whether the AI agent can transfer calls. To '''enable transfers''', click the '''Allow AI agent to transfer calls to specific destinations''' checkbox, then add a '''label''' to describe your transfer scenario(s) (e.g., "Sales Team", "Support Line") or the name of the given person (e.g. "John Doe").

Then, add as many destinations as you wish from:
* [[Sub_Accounts|Internal Extensions]]
* Phone numbers (DID)
* [[Phone_book|Phonebook speed dial entries]]

[[File:IA advanced 2.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Knowledge Base ===

In this section, you define the information sources the agent will use to respond to callers. You can add links such as your website, a knowledge base, a FAQ page, or even a Wiki. '''Ensure all links are publicly accessible and readable.'''

'''Optional:''' Enable '''Allow web search for additional information when appropriate''' to supplement responses with live web results.

[[File:AI_Agent_-_Advanced_-_Knowledge_Base.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

== Advanced Tools and Integrations ==

Extensions allow AI Agents to connect with external systems such as CRMs, helpdesks, databases, and internal business applications.

These integrations enable your AI agents to send information, retrieve data, and perform actions. Helping automate workflows and provide more personalized customer interactions.

Extensions are configured from the '''Extensions''' section within the AI Agent configuration page.

There are two types of integrations available:

* Webhooks
* MCP Servers

Each serves a different purpose and can be used independently or together depending on your workflow requirements.

=== Webhooks ===

Webhooks allow your AI Agent to send information to an external system when a specific event occurs during the call lifecycle.

In simple terms:

''"When something happens, send this information to another system."''

Webhooks are commonly used to:

* Create support tickets
* Log call information
* Send call summaries
* Update CRM records
* Trigger internal workflows
* Notify external applications

=== Webhook Configuration ===

The following fields are available when creating or editing a webhook.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Internal identifier
| Unique system identifier used by the AI Agent to reference the webhook.
|-
| Friendly Name
| Display name
| Human-readable name displayed within the Portal.
|-
| Description
| Usage description
| Explains the purpose of the webhook and when it should be used. The AI Agent may use this information when determining whether to execute the webhook.
|-
| Trigger Condition
| Execution timing
| Defines when the webhook is triggered.
|-
| HTTP Method
| Request method
| Defines how data is sent to the destination system. Common methods include POST, GET, PUT, PATCH, and DELETE.
|-
| URL
| Destination endpoint
| Web address that receives the webhook request.
|-
| Parameters
| Data fields
| Information sent to the external system.
|}

=== Parameters ===

Parameters define the information that will be sent to the destination system.

For each parameter, you can specify:

* A dynamic value generated by the AI Agent
* A fixed value that is always sent
* A default value used when information is unavailable

=== Dynamic Values ===

If the Value field is left empty, the AI Agent will attempt to populate it using information collected during the conversation.

Examples include:

* Customer name
* Email address
* Phone number
* Call reason
* Issue description

=== Fixed Values ===

A fixed value will always be sent with the request.

Example:

* priority = normal

=== Default Values ===

A default value will only be used if the AI Agent is unable to determine the information from the conversation.

== Example Parameter Configuration ==

{| class="wikitable"
! Parameter
! Value
! Result
|-
| subject
|
| AI generates a subject based on the conversation.
|-
| description
|
| AI generates a call summary.
|-
| customer_email
|
| AI attempts to capture the caller's email address.
|-
| priority
| normal
| Always sends "normal" as the priority value.
|}

[[File:Webhooks.png|thumb|none|600px]]

= MCP Servers =

MCP (Model Context Protocol) Servers allow AI Agents to interact with external systems in real time during a conversation.

Unlike webhooks, which send information in a single direction, MCP Servers establish a live connection that enables the AI Agent to query external tools and retrieve information while speaking with the caller.

In simple terms:

''"Connect the AI Agent to an external system so it can retrieve information and perform actions during the call."''

== Common MCP Use Cases ==

MCP Servers can be used to:

* Retrieve customer information from a CRM
* Check order status
* Verify product availability
* Access account information
* Search internal databases
* Execute business-specific workflows

Because these actions occur during the conversation, the caller can receive immediate responses without requiring manual intervention.

== MCP Server Configuration ==

The following fields are available when configuring an MCP Server.

{| class="wikitable"
! Field
! Description
! Purpose
|-
| Name
| Connection name
| Friendly name used to identify the server connection within the Portal.
|-
| Transport Type
| Connection method
| Defines how the AI Agent communicates with the MCP Server. Supported options include SSE and HTTP.
|-
| URL
| Server endpoint
| Address of the MCP Server provided by the connected platform.
|-
| Auth Headers
| Authentication credentials
| Security information required to access the external system.
|}

== Authentication Headers ==

Authentication Headers are commonly used to grant access to external systems.

Examples include:

{| class="wikitable"
! Header
! Example Value
|-
| Authorization
| Bearer abc123...
|-
| X-API-Key
| your-api-key
|}

These values are typically provided by the technical team responsible for the connected application.

== Additional Notes ==

Some MCP implementations support advanced initialization options that may be configured through the API.

These settings are typically used for custom integrations and advanced deployment scenarios.

[[File:MCPs.png|thumb|none|600px]]

|}

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

=== Communication Settings ===

In this final section, you can define how the agent interacts at the start of a call and can also build the entire prompt :

* '''Greeting Message''' — Set the initial message delivered when answering a call
* '''System Prompt''' — Define the core instructions that guide the agent's behavior and responses ([[AI_Prompts|see AI Prompts examples here]])

[[File:IA advanced 5.1.png|thumb|none|600px]]

|}

= Linking Your Agent to a DID =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

Once your agent is created, you need to [[Manage_DID#Edit_a_single_DID_number|assign it]] to a phone number (DID) so it can start answering inbound calls.

# Go to '''DID Numbers''' → '''Manage DIDs''' in the customer portal
# Click '''Edit''' on the DID you want to route to the agent
# In the routing destination section, select '''AI Voice Agent''' from the dropdown
# Choose the specific agent you created from the list
# Click '''Apply'''

Your AI Agent will now answer all inbound calls to that DID!

[[File:AI_Agent_-_Manage_DIDs.png|thumb|none|600px]]

|}

= Servers/ Point of Presence (POP) =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |
[[File:Serverspops.png|thumb|none|600px]]

The '''Servers''' section allows you to configure the Point of Presence (POP) used by your AI Voice Agent.

The POP represents the network server location responsible for receiving and processing calls handled by the AI Agent.

This configuration is available when creating or editing an AI Voice Agent in:

* Simple Agent
* Advanced Agent
* Accordion flows

The Servers tab provides a centralized location to define where your AI Agent operates within the network.

== Understanding Point of Presence (POP) ==

A Point of Presence (POP) is the server location associated with your AI Agent.

The selected server determines the infrastructure used when the agent receives and processes calls.

The available server list matches the servers available under your account information.

== Configuration Model Update ==

The Servers tab introduces a new configuration model that separates AI Agent configuration from phone number routing.

{| class="wikitable"
! Previous Model
! New Model
|-
| One AI Agent was tied to one DID
| One AI Agent can be used across multiple DIDs
|-
| The system attempted to synchronize DID and agent assignments when saving routing
| DID routing only stores the selected routing option
|-
| Configuration was associated directly with the phone number
| AI Agent configuration is managed from the Servers tab
|}

== Configuring the Server ==

When configuring an AI Voice Agent, you can select the desired Point of Presence from the available server list.

The selected POP determines where the agent receives and processes incoming calls.

To configure the server:

# Open the AI Voice Agent configuration.
# Navigate to the '''Servers''' section.
# Select the desired Point of Presence.
# Save the configuration.

Once configured, the AI Agent will use the selected server for its call processing operations.

== Multi-DID Support ==

The new configuration model allows a single AI Agent to be assigned to multiple phone numbers.

Each DID can route calls to the same AI Voice Agent while maintaining its own routing configuration.

Example:

{| class="wikitable"
! Phone Number
! Routing Configuration
|-
| DID 315...
| Routes to AI Agent "Reception"
|-
| DID 442...
| Routes to AI Agent "Reception"
|}

The AI Agent configuration is created once, and multiple phone numbers can reference the same agent.

== Benefits ==

The Servers tab improves AI Agent management by allowing:

* Multiple DIDs to use the same AI Agent
* Centralized agent configuration
* Easier server management
* Simplified DID routing
* Greater flexibility when scaling AI call flows

By separating agent configuration from phone number routing, administrators can manage AI Agents more efficiently and support more complex communication environments.

|}

= Frequently Asked Questions =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

'''Q: Can the AI agent handle outbound calls?'''

A: No — AI Agents are designed for inbound calls only. They answer calls made to your DID; they cannot initiate outbound calls.

'''Q: What languages does the agent support?'''

A: English, Spanish, and French.

'''Q: What is the difference between Simple and Advanced?'''

A: The Simple Voice Agent guides you through a fixed set of steps and covers everything most users need: voice, personality, purpose, call routing, and a knowledge base. The Advanced Voice Agent exposes the underlying LLM and TTS model selection, background audio, and (coming soon) MCP servers and webhook tool integrations for more complex use cases.

'''Q: Can I have multiple agents?'''

A: Yes — you can create as many agents as needed and assign each one to a different DID.

'''Q: Can I edit my agent after creating it?'''

A: Yes — from the AI Agents dashboard you can edit, duplicate, or delete any agent at any time.

'''Q: What happens if the agent cannot answer a question?'''

A: The agent will let the caller know it does not have that information. If call transfers are configured, it can route the caller to a human agent instead.

'''Q: Does the agent answer calls 24/7?'''

A: Yes — once assigned to a DID, the agent answers all inbound calls at any hour.

'''Q: Does the AI agent work with my existing DID?'''

A: Yes — any eligible DID can be routed to an AI Agent from '''DID Numbers → Manage DIDs'''.

'''Q: What does "(Beta)" mean?'''

A: The feature is in active development. Some capabilities — such as Advanced Tools and Integrations — are not yet available, and behaviour may change before the general release.

{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #fef2f2 0%, #fee2e2 100%); border: 1px solid #fca5a5; border-radius: 8px; padding: 25px; margin: 25px 0; box-shadow: 0 2px 10px rgba(248, 113, 113, 0.1);"
|-
| style="text-align: left;" |

We will keep populating this FAQ as questions come along. '''Thanks in advance for your feedback, support and questions!'''

|}

|}

= Need Help or Got Feedback? =

{| cellspacing="0" style="width: 100%; background: white; border: 1px solid #e2e8f0; border-radius: 12px; padding: 25px; margin: 20px 0; box-shadow: 0 2px 10px rgba(0,0,0,0.06);"
|-
| style="vertical-align: top;" |

<div style="font-size: 1.1em; font-weight: 600; color: #1e293b; margin-bottom: 15px;">Support resources</div>

* '''Email''' — [mailto:support@voip.ms support@voip.ms]

'''When reporting an AI Agent issue, include:'''
* The name of the agent and the DID it is assigned to
* The date and time of the call, including the UniqueID found in the CDR
* A description of the behaviour observed vs. what was expected

|}

[[Category:Guides]]

Issabel

2026-03-09T20:10:10Z

Drouleau: Created page with "{| cellspacing="0" style="width: 100%; background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%); border: 1px solid #e2e8f0; border-radius: 8px; padding: 35px; margin-bottom:..."

API Overview

2026-03-05T20:52:32Z

Albert: Correct Email address

Account Verification

2026-03-05T19:59:21Z

Drouleau:

VoIP.ms PBX

2026-03-05T19:18:51Z

Drouleau:

Ringotel

2026-01-26T16:53:10Z

Scomtois: /* Connect to VoIP.ms (PBX) */

[[File:VoIP.ms_Ringotel_Logo.png|right|300px]]
'''Ringotel''' is a cloud-based softphone and unified communications platform designed to work with standard SIP-based VoIP systems.
It provides features such as voice calling, messaging, presence, and video across desktop and mobile devices, while simplifying deployment and management for service providers and enterprises. Ringotel operates as a secure VoIP tunnel that routes SIP traffic between users and an existing PBX or VoIP system, reducing infrastructure complexity and improving reliability.

Ringotel supports centralized user provisioning and management through an admin portal or API, allowing automated onboarding, configuration, and device setup. It also offers integration options with CRM systems, messaging services, and business tools, and includes features such as push notifications, call recording, visual voicemail, BLF (busy lamp field), and rich messaging.

The platform is compatible with most standard SIP PBXs and telephony systems, enabling VoIP providers and organizations to extend their existing voice infrastructure to softphone users without deploying additional VPNs or session border controllers.

----

== Pre-Requisites ==
Before configuring Ringotel Shell, ensure the following requirements are met:

* You must have a Ringotel account. After account creation, you will be redirected to the softphone provisioning portal.
* Prepare Organization details - [https://help.ringotel.com/en/articles/11187474-softphone-provisioning Ringotel KB]:
** Organization Name
** Domain (Ringotel subdomain)
** Region closest to your users.
* Prepare connection details:
** '''VoIP.ms''' — Create a Sub‑Account with User/Password authentication.

== VoIP.ms Sub-Account Specification ==
:: [[File:VoIP.ms_Ringotel_SubAccount-Creation.png|500px|none]]

----
<div style="margin-left:50px;
clear:left;
padding:5px;
border-left: 6px solid rgb(66, 192, 251, 0.8);
box-shadow: 8px 6px 9px -2px #f2f2f2;
background-color: rgba(66, 192, 251, 0.05);
width:70vw;">

'''💬 Notes'''
: 🧱 NAT / Firewall Notes
: If your PBX is behind a NAT firewall, you may need to allow incoming connections from Ringotel server IP addresses in your firewall or security appliance settings. [https://help.ringotel.com/en/articles/11190222-configure-firewall-to-work-with-ringotel See related firewall documentation for details].

</div>
----

== Create an Organization ==
: 1. Go to '''Organizations''' in the Ringotel Shell portal.
: 2. Click '''Create Organization'''.
: 3. Fill required fields:
::* Organization Name
::* Domain (unique subdomain)
::* Region (closest to user base)
: 4. (Optional) Configure onboarding language, tags, and additional settings.
: 5. Click '''Next''' to complete the organization setup.

== Create a Connection ==
A Connection defines how Ringotel communicates with your PBX or SIP trunk provider.

=== Connect to VoIP.ms (SIP Trunk Provider) ===
:1. Within the organization, click '''Create Connection'''.
:2. Select '''Connect to a SIP Trunk Provider'''.
:3. Enter the VoIP.ms details:
::* POP server address
::* Sub‑Account Username
::* Sub‑Account Password
::* Check '''Registration'''
::* Use the same Sub‑Account username for: Number, Username, and Authname fields
:4. Click '''Next''' to finish.
:: [[File:VoIPms_Ringotel_CreateConnectionSIPTrunk.png|500px|none]]

=== Connect to VoIP.ms (PBX) ===
:1. Select '''Connect to a PBX server'''.
:2. Complete the following field:
::* '''Connection name''': Define a connection name for your reference.
::* '''Protocol''': Select UDP or TCP. ''(To use SIP traffic encryption, select SIP-TLS)''
::: *If you have selected SIP-TLS for SIP traffic encryption, you need to enable SIP traffic encryption on your Sub Account)
::* '''Domain or IP address''': indicate your preferred pop server.
::* ''Country: Optional. ℹ️ To use this feature, your DID needs have "Dial Mode" set to "E164". ''
:::[[File:VoIPms_Ringotel_CreateConnectionSIPPBX.png|550px]]

:3 Click '''Advanced settings'''
::* '''Audio codecs''' Check the following codecs '''G.711 Ulaw'''
::* '''Miscellanous''' '''Display Name''': Specify your Outbound CallerID Name
::* '''Registration TTL''': indicate '''120''' secondes
::: [[File:VoIPms_Ringotel_CreateConnectionSIPPBX_Advanced_AudioCodecs.png|350px]][[File:VoIPms_Ringotel_CreateConnectionSIPPBX_Advanced_Misc.png|350px]]
:4. Save the connection.

----

== 4. Add Users ==
:1. Navigate to '''Users''' inside your organization.
:2. Click '''Add User'''.
:3. Provide:
::* Name
::* Email (for onboarding instructions)
::* Assigned Connection (if multiple connections are created)
::* SIP credentials (auto-filled when PBX integration is active)
:4. Save the user to automatically generate onboarding links.

----

= VoIP.ms SMS/MMS Integration with Ringotel =
:This section describes how you can enable the '''SMS and MMS messaging''' for your DID numbers using '''Ringotel'''.
:Once configured, SMS and MMS messages sent to your VoIP.ms DID can be sent and received directly from Ringotel applications.

== Overview ==
VoIP.ms supports SMS and MMS on compatible DID numbers. By integrating VoIP.ms with Ringotel, you can:
:* Send and receive SMS/MMS using VoIP.ms DID numbers
:* Assign numbers to individual users or teams
:* Manage conversations from desktop and mobile applications

<div style="margin-left:50px;
padding:5px;
border-left: 6px solid rgb(208, 149, 45, 0.8);
box-shadow: 8px 6px 9px -2px #f2f2f2;
background-color: rgba(208, 144, 45, 0.08);
width:70vw;">

🔐 '''IMPORTANT''' ⚠️
: : '''Note:''' SMS via integrations requires the '''Ringotel Pro''' plan.
</div>

== Prerequisites ==
Before starting, ensure you have:
* An active '''VoIP.ms account'''
* One or more '''SMS-capable DID numbers'''
* An active '''Ringotel organization''' with Pro features enabled
* Administrator access to both VoIP.ms and Ringotel

== Enable SMS Integration in Ringotel ==

# Log in to the '''Ringotel Admin Portal'''
# Open your organization
# Navigate to '''Features'''
# Enable '''SMS via Integrations'''
# Save changes
# Open the '''Integrations''' tab
# Select '''VoIP.ms''' and click '''Set up Integration'''
# Copy the '''Webhook URL''' (required for VoIP.ms configuration)

== Configure the DID Number in VoIP.ms ==

=== Enable SMS/MMS on the DID ===

# Log in to the '''VoIP.ms customer portal'''
# Go to '''DID Numbers → Manage DID(s)'''
# Select the DID number and click '''Edit'''
# Under '''Message Service (SMS/MMS)''':
## Enable '''SMS/MMS'''
# Enable '''SMS/MMS URL Callback'''
# Paste the Ringotel Webhook URL and append the following parameters:

<div style="margin-left:50px;
padding:5px;
font-family: Consolas, Monaco, Lucida Console, Liberation Mono, DejaVu Sans Mono, Bitstream Vera Sans Mono, Courier New, monospace;
color: silver;
border-left: 6px solid rgb(208, 56, 45, 0.8);
box-shadow: 8px 6px 9px -2px #f2f2f2;
background-color: black;
width:58%;">

: <nowiki>https://shell.ringotel.co/services/Voipms/aXXXXXXXXXXXXXXXXXXXX?id={ID}&to={TO}&from={FROM}&message={MESSAGE}&files={MEDIA}</nowiki>

: The final URL should look similar to the following:
: <nowiki>https://shell.ringotel.co/services/Voipms/a15945585810414401989?id={ID}&to={TO}&from={FROM}&message={MESSAGE}&files={MEDIA}</nowiki>

</div>

: 7. Save the DID settings

== Enable VoIP.ms API Access ==
Ringotel communicates with VoIP.ms using the VoIP.ms API.

:1. In the VoIP.ms portal, navigate to '''Main Menu → SOAP and REST/JSON API'''
:: [[File:VOIPMS_Main_Menu_RestJsonAPI.png|500px|none]]

:2. Set an '''API Password'''
:3. Enable the API if it is not already enabled
:4. Under '''Enable IP Addresses''', add the following Ringotel IP addresses:

<div style="margin-left:50px;
padding:5px;
font-family: Consolas, Monaco, Lucida Console, Liberation Mono, DejaVu Sans Mono, Bitstream Vera Sans Mono, Courier New, monospace;
color: silver;
border-left: 6px solid rgb(208, 56, 45, 0.8);
box-shadow: 8px 6px 9px -2px #f2f2f2;
background-color: black;
width:58%;">

: 54.145.196.146, 18.130.161.112, 3.0.222.77

</div>
:5. Save the API settings

:: [[File:VOIPMS_API_Ringotel-IPs.png|500px|none]]

== Complete the Integration in Ringotel ==
:After setting up your API password and the IP addresses in your VoIP.ms portal, return to your Ringotel Admin portal to complete the connection.
:## Your '''VoIP.ms login email'''
:## Your '''VoIP.ms API password'''
:# Click '''Save & Continue'''

:: [[File:VoIPms_Ringotel_CreateConnectionSIPTrunk.png|500px|none]]

== Add SMS Numbers and Assign Users ==
# Add your VoIP.ms DID numbers with SMS enabled
# Assign users who can send and receive messages
# Enter phone numbers in '''national format''' (for example, <code>5033889028</code> for US/Canada)
# Configure optional settings:
## '''Session stickiness''' (keeps conversations assigned to the same user)
## '''Number reformatting''' (prevents duplicate conversation threads)
## '''Sender name in messages'''
## '''Auto-replies''' and opt-out messages
# Save the configuration

Users may need to '''log out and log back in''' to access SMS features.

== Notes and Limitations ==

<div style="margin-left:50px;
padding:5px;
border-left: 6px solid rgb(208, 56, 45, 0.8);
box-shadow: 8px 6px 9px -2px #f2f2f2;
background-color: rgba(51, 51, 51, 0.08);
width:70vw;">

⚠️ '''LIMITATIONS'''
: ➜ SMS and MMS availability depends on the DID type and country
: ➜ MMS support may vary by carrier
: ➜ Short codes and toll-free numbers may require additional configuration

</div>