Sam Machin
e6e039e0f2
add alert verb ( #1270 )
...
* add alert verb
* update dependencies
* Update package-lock.json
* remove await taskDone
2025-07-10 07:39:42 -04:00
Hoan Luu Huu
337c1cded0
fixed transcription is not received when call is terminated ( #1259 )
...
* fixed transcription is not received when call is terminated
* wip
* fixed failing testcases
* wip
* wip
* wip
* wip
* should not do gracefulshutdown on stopAmd
2025-07-09 10:20:09 -04:00
Dave Horton
444abcb036
(fd 1056) if no payload returned from referHook in dial then dont do anything ( #1271 )
2025-07-07 12:50:46 -04:00
Hoan Luu Huu
c82a835e70
FD_1079: tts modules response_code = 0 should make say fail to exec. ( #1269 )
...
* FD_1079: tts modules response_code = 0 should make say fail to exec.
* fixed tts azure does not have response code
* fixed tts error does not raise alarm
* wip
* fixed
2025-07-07 07:59:29 -04:00
Dave Horton
7691af30de
Fix/dial refer ( #1264 )
...
* Revert "Update dial.js (#1243 )"
This reverts commit 259dedcded
2025-06-28 15:01:09 -04:00
Hoan Luu Huu
ab83b21979
support inworld tts ( #1262 )
...
* support inworld tts
* wip
* wip
2025-06-27 10:05:18 -04:00
Hoan Luu Huu
f18b62e165
support ultravox agent id ( #1254 )
...
* support ultravox agent id
* wip
2025-06-23 09:37:10 -04:00
Hoan Luu Huu
8c67c05d87
fixed bargin task loop forever ( #1253 )
2025-06-22 06:20:24 +02:00
Hoan Luu Huu
3f11ee58a7
fixed dub playOnTrack loop forever ( #1247 )
2025-06-18 21:37:32 +02:00
Hoan Luu Huu
5be6c54339
support mod_cartesia_transcribe ( #1245 )
2025-06-17 20:54:26 +02:00
Sam Machin
259dedcded
Update dial.js ( #1243 )
2025-06-13 18:23:40 +02:00
Dave Horton
b70fea69cc
Fix/dial unhandled rejection ( #1239 )
...
* fix bug with race condition in dial which could spike cpu due to unhandled exception
* update to 0.2.12 speech-utils with azure ssml fix
* minor
2025-06-11 11:40:51 +02:00
Hoan Luu Huu
b0b74871e7
support say stream with text ( #1227 )
...
* support say stream with text
* wip
* wip
* wip
* wip
* update verb specification
2025-06-10 16:56:44 +02:00
Rohan Sreerama
e686a11808
fix(play): fixes ep null issue ( #1233 )
...
* fix(play): fixes ep null issue
* chore(play): fixing formatting
* chore(play): update syntax
* chore(play): updates
* fix(play): updated fix
* fix(play): updated fix
---------
Co-authored-by: rsreerama3 <rsreerama3@gatech.edu >
2025-06-05 14:57:35 -04:00
Dave Horton
8e9ab83ca4
Fix/env vars rest dial ( #1225 )
...
* rest dial needs to support env vars
* wip
2025-05-30 10:14:44 -04:00
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
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
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
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
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
Sam Machin
0bf2013934
add default model ( #1147 )
2025-04-22 09:49:24 -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
rammohan-y
0a541e089d
Fix for https://github.com/jambonz/jambonz-feature-server/issues/1138 ( #1139 )
2025-04-04 09:02:18 -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
