ben.carrasco/jambonz-feature-server
1
0
Fork 0
mirror of https://github.com/jambonz/jambonz-feature-server.git synced 2025-12-19 04:17:44 +00:00
Code Issues Packages Projects Releases Wiki Activity
1,176 Commits 152 Branches 330 Tags
main
Commit Graph

940 Commits

Author SHA1 Message Date
Dave Horton
b734952855 proper handling of case when amd fails because no speech credentials (#1220) 2025-05-28 13:01:08 -04:00
Hoan Luu Huu
4990b1fb68 fix mod dub throw undefined reference (#1209) 2025-05-28 09:58:33 -04:00
Hoan Luu Huu
3475f39b1d support deepgram model_id in speechCredential (#1213) 2025-05-28 08:00:56 -04:00
Hoan Luu Huu
690a7fcd55 add ws msgid to telemetry span if it's ws requestor (#1215) 
* add ws msgid to telemetry span if it's ws requestor

* wip
 2025-05-28 07:51:59 -04:00
Dave Horton
760394aa5e Revert "fix: member mute on conference (#1048)" (#1216) 
This reverts commit 761b7f26e7.
 2025-05-28 07:21:24 -04:00
Dave Horton
603dd482bc add a bit more info logging to gather (#1211) 2025-05-26 09:34:21 -04:00
Dave Horton
f670626cf7 google gemini set default model to models/gemini-2.0-flash-live-001 2025-05-22 08:12:58 -04:00
Hoan Luu Huu
b92a9c700e fixed google s2s mcp initiate wrong functionDeclarations (#1203) 
* fixed google s2s mcp initiate wrong functionDeclarations

* populate model from llm verb to google setup message
 2025-05-18 20:15:26 -04:00
Anton Voylenko
761b7f26e7 fix: member mute on conference (#1048) 2025-05-18 14:11:56 -04:00
Dave Horton
76df58bfc2 fix logging in start task msg (#1202) 
* fix logging in start task msg

* generate uuids using native crypto lib
 2025-05-16 16:54:25 -04:00
Hoan Luu Huu
9585018147 support whisper instructions (#1198) 
* support whisper instructions

* wip

* update speech utils and verb specification
 2025-05-13 09:44:00 -04:00
Hoan Luu Huu
d7884a837a update deepgram voice agent (#1191) 
* update deepgram voice agent

* fix lint

* wip

* wip
 2025-05-13 07:43:48 -04:00
Dave Horton
ca0bf36815 dont apply snake casing to either env vars or tool call args (#1194) (#1197) 2025-05-12 12:56:58 -04:00
Sam Machin
6b68d32e2c end if last_word_end is -1 (#1196) 
* end if last_word_end is -1

* lint
 2025-05-12 12:11:32 -04:00
rammohan-y
8217a76697 Removed this.name from Task constructor, as LLM's names are populated post calling the base construction (#1192) 
Also fixed a jslint error
 2025-05-12 09:14:33 -04:00
rammohan-y
5c8237b382 Feat 1179 race issue with play verb (#1183) 
* Fixed race issue between queueCommand false and queueCommand true when play task is involved

https://github.com/jambonz/jambonz-feature-server/issues/1179

* removed unnecessary emitter

* added destroy mechanism for stickyEventEmitter

* clearing stickyEventEmitter

* memory leak fix
 2025-05-11 20:25:48 -04:00
Hoan Luu Huu
8b18532f31 fixed tts streaming buffer cannot reset timeoutwhen lastUpdateTime is short (#1184) 
* fixed tts streaming buffer cannot reset timeoutwhen lastUpdateTime is short

* wip
 2025-05-07 10:26:11 -04:00
rammohan-y
e4bb00b382 Send stop-playback event (#1186) 
* Send stop-playback event

https://github.com/jambonz/jambonz-feature-server/issues/1185

* check if not notified in playback-stop, ensure that the stop-playback is sent when kill-playback is sent
 2025-05-07 08:59:59 -04:00
Hoan Luu Huu
14295dcebc support google s2s (#1169) 
* support google s2s

* wip
 2025-05-07 07:20:33 -04:00
Hoan Luu Huu
4d68c179ea sip_decline release callSession if ws requestor is used (#1182) 2025-05-06 10:01:36 -04:00
Hoan Luu Huu
6205959f53 fix microsoft stt max client buffer size error for transcribe verb (#1173) 2025-04-29 09:41:24 -04:00
Hoan Luu Huu
ed92cb2632 update speech utils 0.2.7 (#1177) 
* update speech utils 0.2.7

* wip
 2025-04-29 08:26:09 -04:00
Sam Machin
3098e04ed6 send env_vars in callHook (#1175) 
* send env_vars in callHook

* lint

* add try/catch
 2025-04-28 09:51:37 -04:00
Hoan Luu Huu
7e2fe72b6c fix say verb cannot failover if tts_response-code != 2xx (#1174) 2025-04-28 08:46:08 -04:00
Hoan Luu Huu
c2666b7a09 fixed deepgram gather cannot be timeout on empty transcription with continueAsr (#1171) 2025-04-28 08:36:31 -04:00
Hoan Luu Huu
9d54ca8116 Jambonz support Model context protocol (MCP) (#1150) 
* Jambonz support Model context protocol (MCP)

* merged mcp tools with existing llmOptions.tools

* support list of mcp servers

* wip

* wip

* wip

* fix voice agent

* fix open-ai

* fix review comment

* fix deepgram voice agent

* update verb specification version
 2025-04-24 06:50:53 -04:00
Sam Machin
472f4f4532 clientTools over webhooks (#1167) 
* clientTools over webhooks

* lint

* simpler toolHook response
 2025-04-23 09:15:16 -04:00
Hoan Luu Huu
15b583ef2c only connect to drachtio server if connected to freeswitch (#1123) 
* only connect to drachtio server if connected to freeswitch

* wip

* wip
 2025-04-22 09:55:39 -04:00
Sam Machin
0bf2013934 add default model (#1147) 2025-04-22 09:49:24 -04:00
rammohan-y
182c310191 remove video from sdp in case of reInvite if the call is audio call (#1159) 
https://github.com/jambonz/jambonz-feature-server/issues/1158
 2025-04-18 09:33:16 -04:00
Sam Machin
4e74bab728 handle errors in createing call (#1164) 
* move createCall into the try/catch and add a completionReason to results for errors

* add default completionReason

fixes #1165

* lint
 2025-04-17 07:43:22 -04:00
rammohan-y
87195b6444 Stop tts streaming, when bargeIn is enabled for gather verb and input is detected (#1154) 
https://github.com/jambonz/jambonz-feature-server/issues/1153
 2025-04-14 09:18:50 -04:00
Dave Horton
305facb03b Fix/11labs no client config (#1149) 
* update to verb specs

* add parameter to api call when there is not client config provided
 2025-04-12 10:36:35 -04:00
Dave Horton
d310ba0ed1 reduce verbosity of logging (#1145) 2025-04-09 15:36:58 -04:00
Hoan Luu Huu
77f0fc85a3 ell tts support speech and pronunciation_dictionary_locators (#1137) 2025-04-09 12:32:06 -04:00
Sam Machin
c708b7d007 fix initial message format (#1144) 2025-04-09 10:43:07 -04:00
Hoan Luu Huu
343b382373 fixed ws-requestor missing hook for dial:confirm (#1143) 2025-04-09 07:29:08 -04:00
rammohan-y
0a541e089d Fix for https://github.com/jambonz/jambonz-feature-server/issues/1138 (#1139) 2025-04-04 09:02:18 -04:00
rammohan-y
d910981b1a Allow hangup verb on siprec call (#1136) 
* Allow hangup verb on siprec call
https://github.com/jambonz/jambonz-feature-server/issues/1135

* added sip:decline to AllowedSipRecVerbs
 2025-04-04 08:23:39 -04:00
Hoan Luu Huu
3f2744f032 fixed replaceEndpoint offer single codec that callee does not support (#1131) 2025-04-03 07:58:39 -04:00
Dave Horton
fcaf2e59e7 initial changes for openai stt (#1127) 
* initial changes for openai stt

* wip

* wip

* wip

* wip

* wip

* make minBargeinWordCount work for openai

* wip

* wip

* wip

* wip

* wip

* wip

* wip

* wipp

* wip

* wip

* wip

* openai stt: support for prompt templates

* lint

* wip

* support openai semantic_vad

* wip

* transcribe supports openai stt

* sip

* wip

* wip

* refactor list of stt vendors that dont need to be restarted after a final transcript

* cleanup

* wip

* cleanup

* wip

* wip

* wip

* remove credentials from log

* comment
 2025-03-28 13:14:58 -04:00
rammohan-y
ee846b283d Feat 1120 video call - remove video media from SDP if the call is audio call (#1124) 
* sending jambonz:error when the incoming message is not parsable

https://github.com/jambonz/jambonz-feature-server/issues/1094

* writing an alert when incoming paylod is invalid

* added content to the jambonz:error payload

* removing video media from sdp if the call is an audio call. This is to avoid sending video media to destination if the incoming call is an audio call

* calling removeVideoSdp only when the environment variable JAMBONES_VIDEO_CALLS_ENABLED_IN_FS is set to true, this will ensure there are no regression issues for audio calls

* fixed jslint errors
 2025-03-28 12:56:08 -04:00
Hoan Luu Huu
acdb8695a0 allow cartesia model_id is override from synthesizer option (#1130) 2025-03-27 13:37:57 -04:00
Hoan Luu Huu
f33f197e8d gather say support ttstream (#1128) 2025-03-27 07:19:19 -04:00
Sam Machin
9c437ab687 use deepgramOptions.model (#1126) 
* use deepgramOptions.model

* lint

* Update transcription-utils.js
 2025-03-24 12:25:29 -04:00
rammohan-y
d36e6b4c22 set the detected language as language_code when deepgram detects the language (#1116) 
https://github.com/jambonz/jambonz-feature-server/issues/1115
 2025-03-11 12:16:29 -04:00
Sam Machin
3120dbc3e0 Feature: add digitCount to amd-utils (#1111) 
* add digitCount to amd-utils

* linting

* bump verb-specs
 2025-03-06 12:01:51 -05:00
Hoan Luu Huu
8b8283e603 ws requestor should store initial sessionData when sending session:adulting (#1110) 2025-03-06 07:42:47 -05:00
Dave Horton
29de4b8878 fix crashing error with some media timeout scenarios (#1108) 2025-03-05 09:48:40 -05:00
Sam Machin
fa5fc1af9f allow transcribe_status update on Listen/Transcribe tasks (#1107) 2025-03-04 12:41:27 -05:00