Changelog

New Features

1. Adds support for Google Gemini speech-to-speech LLM. See example application here. Speech-to-speech LLMs now supported include: Gemini, Ultravox, OpenAI, Deepgram, and elevenlabs.
2. Added MCP client support to the llm verb. You can now specify an array of one or more MCP servers in the mcpServers property of the llm verb and jambonz will query those MCP servers and automatically create tools for the LLM to call based on the tools exposed by each of the MCP servers. For an example, see the google gemini sample app.
3. Added support for application environment variables, which are special configuration variables that can be set in the jambonz portal for an application to customize the application behavior. This enables hosting of a single application that can then be customized for different customers without having to modify source code.
4. Added support for Deepgram Aura-2 TTS model and voices
5. Added support for Rime Arcana model
6. Added support for PlayHT on-prem deployments.
7. Added support for using outbound sip proxy when registering
8. Added support for providing instructions to Whisper TTS
9. Added new voice for nvidia TTS

Bug fixes

• Various stability fixes including for issues which caused intermittent Freeswitch crashes.
• Fixed deepgram gather cannot be timeout on empty transcription with continueAsr. PR
• Fixed say verb cannot failover if tts_response-code != 2xx. PR
• Fixed microsoft stt max client buffer size error for transcribe verb. PR
• sip_decline release callSession if ws requestor is used. PR
• Send stop-playback event. PR
• Fixed tts streaming buffer cannot reset timeout when lastUpdateTime is short. PR
• Fixed issue with Deepgram STT not returning transcript when last_word_end is -1. PR
• Fixed issue muting member in conference. PR
• Fixed API server crash when admin query voip-carrier. PR
• Fixed issue where we incorrectly saved an obscured API credential for recording, leading to failures authenticating. PR
• Fixed an issue where updateCall responding with 202 caused an error. PR
• Fixed an issue in the portal where the wrong recording bucket region was displayed. PR

SQL changes

ALTER TABLE applications ADD COLUMN env_vars TEXT

Availability

• Available now on jambonz.cloud
• Available now with devops scripts for subscription customers

Questions? Contact us at support@jambonz.org

Elevenlab conversational AI bug fixes, readonly portal users and stability improvements

1. Fixes an issue where the initial client configuration message for Elevenlabs Conversational AI was improperly formatted.
   
   PR

2. Adds support for speed and pronunciation_dictionary_locators for Elevenlabs TTS.
   
   PR

3. Addresses memory allocation issue in freeswitch modules that could lead to intermittent crashes. (Fixed in freeswitch-modules@2.2.26).

4. Add support for throttling outbound registrations and disabling. Also added support for disabling outbound REGISTERs or NOTIFYs based on specific failure codes returned from the far end trunk.
   
   PR, PR

5. Fixes issue where confirm hook on a dial verb was not working over a websocket connection.
   
   PR

6. Adds support for creating portal users with readonly access.
   
   PR

7. Disable password managers (e.g. LastPass, etc) on some forms where they were incorrectly auto-filling data, leading to confusion over why the form was not submitting.
   
   PR

8. Fixes issue with failing re-INVITE due to unsupported codec.
   
   PR

9. Allows hangup verb to be used in a siprec call.
   
   PR

10. Fixes scenario where we have two config verbs, first config having hints, but second one not having hints, then the transcribe verb generating a rutime error.
    
    PR

11. Reject portal logins with better error message if a user that signed up using ouath tries to sign in using email and password.
    
    PR

12. Allow a readonly portal user to change their password.
    
    PR

Add support for OpenAI Streaming STT and other improvements

1. Adds support for OpenAI Speech-to-text. Please see related options here and review this article a discussion of how to use the OpenAI STT prompt feature.
   
   PR, PR, and PR.

2. Support Cartesia sonic-2 and sonic-turbo models.
   
   PR

3. Fixes issue with use of streaming say in gather verb.
   
   PR

4. Better support for passing webrtc video calls.
   
   PR

5. Fixes issue when using language detection feature with Deepgram.
   
   PR

6. Fixes an issue showing incorrect speech synthesizer in applications view in the portal.
   
   PR

7. Write options ping failure alert once instead of repeatedly.
   
   PR

8. Fixes issue where lengthy LLM prompts for ultravox, elevenlabs, and deepgram were being truncated.

Additional log visibility, improvements to AMD, and more

1. Adds log viewer to jambonz portal (AWS only) to enable easier troubleshooting of calls.
   
   PR, Issue

2. Improves answering machine detection by listening for strings of digits in addition to other heuristics.
   
   PR

3. Add support for username and password authentication to redis.
   
   PR

4. Fixes crashing error with some media timeout scenarios
   
   PR

5. Adds support for pausing transcriptions on Listen and Transcribe verbs.
   
   PR

6. When a session uses live call control and a session:adulting message is sent to the application, customer data is now included.
   
   PR

7. Fixes an issue when a call is ended via the API live call control the call_terminated_by field is now ‘jambonz’.
   
   PR

8. Filters the carrier list by account when creating a new phone number.
   
   PR

9. Usability improvements when configure a websocket-based application URL in the jambonz portal.
   
   PR

10. Allows the Recent Calls API to return more than 25 calls at a time.
    
    PR

11. Smooth outbound SIP registrations to avoid spikes.
    
    PR

Audio Improvements with Bidirectional Streams, Ultravox Enhancements, AWS Autoscaling fixes and more

1. Allows the url property in a listen verb to be a relative URL when used in a websocket application. This allows developers to create a single websocket app that handles both jambonz commands and bidirectional audio streams.
   
   See this realtime translation example that uses openAI and bidirectional audio streams, where the url property is a relative URL and the app handles both jambonz commands and the audio stream.
   
   PR, Issue

2. Fixes an intermittent issue with audio issue with crackling noise on bidirectional audio streams.

3. When an application redirects to a new absolute URL, update the base requestor so that future relative URLs are resolved relative to the new URL.
   
   PR, Issue

4. Fixes an issue where the final transcript in a conversation initiated with the dial verb was sometimes not collected if the caller hung up quickly after their final utterance.
   
   PR, Issue

5. Adds support for sending an input_text_message to Ultravox.ai during a speech-to-speech session. This enables the application to dynamically direct the conversation through means other than the caller’s voice.
   
   PR

6. Fixes an issue with intermittent failure to clean up media server resources after a call completes.
   
   PR Issue

7. Webapp no longer shows Messaging webhook as SMPP is a deprecated feature for the time being (lack of customer demand).
   
   PR, Issue

8. Fixes database upgrade script which had previously misnamed a column.
   
   PR Issue

9. Fixes an issue with AWS autoscaling where incorrect SNS topic name was used, leading to unnecessarily long scale-in durations.
   
   PR

10. When sending a REFER over sips the Contact header should also use sips scheme.
    
    PR

Conferencing Enhancements and Minor Fixes

1. Adds support for receiving sip requests during a conference call.
   
   PR, Issue

2. Sends new error message over websocket to application when an incoming request from the application is not valid.
   
   PR Issue

3. Fixes a typo with the variable name used to store the AWS SNS topic arn (only relevant for AWS deployments).
   
   PR

Improve Ultravox Integration

1. Adds support for sending the Ultravox call identifier to the jambonz app so that it can be used for tracking and troubleshooting purposes.
   
   PR

2. Update to drachtio-srf 5.0.2

Important STT Improvements for Deepgram and Speechmatics, Support for Outbound SIP Proxy and more

1. Adds support for carriers that require us to send them calls through an outbound sip proxy.
   
   PR, PR PR, Issue

2. Reject call attempts on hosted jambonz systems where the account has no active subscription.
   
   PR

3. Improve Deepgram integration by ignoring UtteranceEnd event from Deepgram when we have unprocessed words; in this scenario it is better to continue to wait for the unprocessed words to become finalized.
   
   PR Issue

4. Fixes issue where exception thrown when a new application URL is provided during a call and the request to that URL fails.
   
   PR

5. Improves handling of errors when handling tts:tokens requests to stream text tokens from an LLM.
   
   PR

6. Fixes timeout issues when working with speechmatics STT.
   
   PR

7. Adds a response time metric when using tts streaming.
   
   PR

8. Fixes an issue where when using the dialMusic property in a dial verb, the music could play endlessly.
   
   PR, Issue

9. Allows the Deepgram nodelay property to be explicitly set.
   
   PR, Issue

10. Enhances the createCall REST API to allow the caller to specify a sip proxy to send the INVITE through.
    
    PR

11. Fixes issue where an incoming REGISTER with invalid sip uri in the From or To header causes an exception.
    
    PR, Issue

12. Supports recording an incoming SIPREC call using the jambonz recording feature.
    
    PR

New Deepgram And Rime Labs Features

1. Adds support for Deepgram keyterms feature.
   
   PR

2. Add support for Rime Labs new mistv2 model and additional voices.
   
   PR PR

3. Fixes an issue where recognizer property was used without including a language and the default application setting for language was not used.
   
   PR

Adding Voxist as new STT Vendor, ElevenLanbs Conversational AI Agents and more

1. Adds support for Voxist STT.
   
   PR

2. Enhance TTS caching to account for the model of the TTS engine as well as vendor and other properties.
   
   PR, Issue

3. Adds support for using ElevenLabs conversational AI agents.
   
   PR, PR

4. Adds support for setting the speech recognition mode for Azure STT. The allowed values are CONVERSATION, DICTATION and INTERACTIVE.
   
   PR, Issue

5. Fixes an issue where a re-INVITE received during a dial operation could cause an exception.
   
   PR, Issue

6. Adds support for streaming TTS using Rime Labs.
   
   PR

7. Supports fetching elevenlabs models by api-key.
   
   PR

8. Fixes some issues with tracking call counts on the SBC.
   
   PR