Changelog

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

New Features

• support for TTS streaming, enables streaming of text tokens from LLMs directly to TTS engines. Currently, Deepgram, Elevenlabs, Cartesia, and Rimelabs are supported as TTS engines.
• support for Deepgram Voice Agent speech-to-speech service (see example app).
• support for Ultravox.ai speech-to-speech service (see example app).
• support for Cartesia as TTS engine
• updated Speechmatics support with additional options
• major improvements in feature server performance, particularly with bidirectional audio, TTS and dub audio inserts
• support for Google speech cloning
• support for Deepgram filler words in STT
• added the ability to create a bidirectional stream on the B leg of a dialed call
• added new speech api to allow developers to implement custom tts streaming solution
• support for handling incoming 3pcc invites (no body) from carriers
• support SIP privacy header
• added ability to send refer custom header to referhook
• added ability to specify the Refer-To display name
• added support for dub verb as a live call control request
• added abjility to export to more than one otel platform
• sending socket close code when there is no response from the websocket app
• rest:dial support timeLimit
• sending reason in X-Reason header when AHD processor giveup
• support kill dial if sd ep is media timeout
• capture system_alert when feature-server is online or offline
• enable dtmf recognition of audible tones for carriers that do not support RFC 2833
• support recents call dropdown filter to have yesterday option
• add ability to filter easily by account in portal when viewing large numbers of accounts

Bug fixes

• update drachtio-srf and fsmrf to main branch releases
• fix inband dtmf does not work in dial verb
• fix for sticky bargein
• Make voicemail hints case insensitive
• fix ConfirmCallSession cannot be played
• fix incorrectly sending final transcript with is_final=false
• fix cannot replace endpoint for adulting session
• A play verb in an actionhookdelay property that contains an invalid url will cause that play to block and subsequent verbs will not be executed
• fixed iamrole from sessionToken to securityToken
• fix to allow hints objects array
• fix for stopping continuos asr when asrDtmfTerminationDigit is configured
• custom stt vendor ws connection should not be closed in asrTimeout
• feature server should send USER call to the sbc sip that is connect with the user (#949)
• fixed dial verb should use calling id from From header (#958)
• rest api: added support for name query parameter for retrieving application
• per RFC 3261 the request-uri of REGISTER must not have userinfo
• Change timer for next REGISTER expires / 2 to avoid delayed registrations

SQL changes

ALTER TABLE google_custom_voices ADD COLUMN voice_cloning_key MEDIUMTEXT;
ALTER TABLE google_custom_voices ADD COLUMN use_voice_cloning_key BOOLEAN DEFAULT false;
ALTER TABLE voip_carriers ADD COLUMN dtmf_type ENUM('rfc2833','tones','info') NOT NULL DEFAULT 'rfc2833';

Availability

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

Questions? Contact us at support@jambonz.org