wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
7,193 Commits 276 Branches 111 Tags
9a718ded1ed2be52043cb23cd8b81ffb8bbaf223
Commit Graph

7193 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Aleix Conchillo Flaqué
9a718ded1e NvidiaTTSService: initialize client on StartFrame 
Initialize client on StartFrame so errrors are reported within the pipeline.
 2026-01-20 08:58:14 -08:00
Aleix Conchillo Flaqué
024809b39a Merge pull request #3503 from pipecat-ai/aleix/ai-service-start-end-cancel 
AIService: handle StartFrame/EndFrame/CancelFrame exceptions
 2026-01-20 08:56:39 -08:00
Aleix Conchillo Flaqué
6cf0d53d00 AIService: handle StartFrame/EndFrame/CancelFrame exceptions 
If AIService subclasses implement start()/stop()/cancel() and exception are not
handled, execution will not continue and therefore the originator frames will
not be pushed. This would cause the pipeline to not be started (i.e. StartFrame
would not be pushed downstream) or stopped properly.
 2026-01-20 08:54:22 -08:00
kompfner
778dacc9a8 Merge pull request #3486 from pipecat-ai/pk/fix-nova-sonic-reset-conversation 
Fix `AWSNovaSonicLLMService.reset_conversation()`
 2026-01-20 10:07:38 -05:00
Paul Kompfner
06b3ecd2d6 In AWS Nova Sonic service, send the "interactive" user message (which triggers the bot response) only after sending the audio input start event, per the AWS team's recommendation 2026-01-20 09:56:25 -05:00
Paul Kompfner
b4d143e39b Add CHANGELOG for fixing AWSNovaSonicLLMService.reset_conversation() 2026-01-20 09:56:25 -05:00
Paul Kompfner
c89083e72e Improve 20e example to ask the bot to give a recap when loading a previous conversation from disk 2026-01-20 09:56:25 -05:00
Aleix Conchillo Flaqué
f03a7175c7 Merge pull request #3501 from pipecat-ai/aleix/improve-eval-numerical-word-prompt 
scripts(eval): give examples to numerical word answers
 2026-01-19 20:22:06 -08:00
Aleix Conchillo Flaqué
aed44c863a scripts(eval): give examples to numerical word answers 
Some models need extra help.
 2026-01-19 14:37:00 -08:00
Mark Backman
cddd6d5b0a Merge pull request #3492 from pipecat-ai/mb/remove-unused-imports 
Remove unused imports
 2026-01-19 14:07:16 -05:00
Mark Backman
11cf891ac8 Manual updates for unused imports 2026-01-19 14:03:22 -05:00
Mark Backman
cc4c3650e1 Merge pull request #3491 from pipecat-ai/mb/update-release-evals 
Add Camb TTS to release evals
 2026-01-19 11:04:05 -05:00
Filipi da Silva Fuchter
5fc46cc450 Merge pull request #3493 from omChauhanDev/fix/globally-unique-pc-id 
fix: make SmallWebRTCConnection pc_id globally unique
 2026-01-19 09:04:48 -05:00
Om Chauhan
990d8386e4 fix: make SmallWebRTCConnection pc_id globally unique 2026-01-18 19:41:51 +05:30
Mark Backman
ce7d823770 Remove unused imports 2026-01-18 08:22:22 -05:00
Mark Backman
0b93c3f900 Add Camb TTS to release evals 2026-01-17 16:27:16 -05:00
Mark Backman
829c5f4604 Merge pull request #3169 from Incanta/hathora 
Add Hathora STT and TTS services
 2026-01-17 16:25:12 -05:00
Mike Seese
dc8ea615d9 add hathora to run-release-evals.py 2026-01-17 10:33:58 -08:00
Mike Seese
a3d206050d move hathora example as requested 2026-01-17 10:31:08 -08:00
Mike Seese
f48a567873 run the linter 2026-01-17 10:30:47 -08:00
Mark Backman
e69ccd8ea7 Merge pull request #3490 from pipecat-ai/mb/on-user-mute-events 
Add on_user_mute_started and on_user_mute_stopped events
 2026-01-17 11:05:15 -05:00
Mark Backman
11924bb980 Add on_user_mute_started and on_user_mute_stopped events 2026-01-17 11:01:46 -05:00
Mark Backman
af89154e96 Merge pull request #3489 from pipecat-ai/mb/fix-azure-tts-punctuation-spacing 
fix: AzureTTSService punctuation spacing
 2026-01-17 11:00:30 -05:00
Mark Backman
1485ea0831 Merge pull request #3488 from pipecat-ai/mb/on-user-turn-idle 
Update on_user_idle to on_user_turn_idle
 2026-01-17 11:00:16 -05:00
Mark Backman
e22bc777d8 Fix spacing for CJK languages 2026-01-17 09:04:50 -05:00
Mark Backman
043403fe23 fix: AzureTTSService punctuation spacing 2026-01-17 08:18:31 -05:00
Mark Backman
1e1160906e Update on_user_idle to on_user_turn_idle 2026-01-17 07:04:27 -05:00
Aleix Conchillo Flaqué
f7d3e63063 Merge pull request #3474 from pipecat-ai/fix/optional-member-access-function-call-cancel 
Fix Pylance reportOptionalMemberAccess in _handle_function_call_cancel
 2026-01-16 22:06:45 -08:00
Paul Kompfner
6fa797c8e4 Fix AWS Nova Sonic reset_conversation(), which would previously error out. 
Issues:
- After disconnecting, we were prematurely sending audio messages using the new prompt and content names, before the new prompt and content were created
- We weren't properly sending system instruction and conversation history messages to Nova Sonic with `"interactive": false`
 2026-01-16 22:31:54 -05:00
Mark Backman
473d39791b Merge pull request #3482 from pipecat-ai/mb/user-idle-in-user-aggregator 
Add UserIdleController, deprecate UserIdleProcessor
 2026-01-16 18:47:10 -05:00
Aleix Conchillo Flaqué
2114abb8c6 add changelog file for 3484 2026-01-16 15:46:29 -08:00
Aleix Conchillo Flaqué
4fb4c26f55 Merge pull request #3484 from amichyrpi/main 
Remove async_mode parameter from Mem0 storage
 2026-01-16 15:44:52 -08:00
Mark Backman
2e8e574ea5 Add UserIdleController, deprecate UserIdleProcessor 2026-01-16 18:44:19 -05:00
Aleix Conchillo Flaqué
84c7e97be2 Merge pull request #3483 from pipecat-ai/aleix/throttle-user-speaking-frame 
throttle user speaking frame
 2026-01-16 15:29:37 -08:00
Amory Hen
a6e7c99d55 Remove async_mode parameter from Mem0 storage 2026-01-17 00:26:38 +01:00
Aleix Conchillo Flaqué
ac3fa7f91f BaseOuputTransport: minor cleanup 2026-01-16 15:15:49 -08:00
Aleix Conchillo Flaqué
6eadad53b2 BaseInputTransport: throttle UserSpeakingFrame 2026-01-16 15:15:49 -08:00
kompfner
b11150f31f Merge pull request #3480 from pipecat-ai/pk/fix-grok-realtime-smallwebrtc 
Fix an issue where Grok Realtime would error out when running with Sm…
 2026-01-16 15:46:27 -05:00
Paul Kompfner
836cf60611 Fix an issue where Grok Realtime would error out when running with SmallWebRTC transport. 
The underlying issue was related to the fact that we were sending audio to Grok before we had configured the Grok session with our default input sample rate (16000), so Grok was interpreting those initial audio chunks as having its default sample rate (24000). We didn't see this issue when using the Daily transport simply because in our test environments Daily took a smidge longer than a reflexive (localhost) pure WebRTC connection, so we would only send audio to Grok *after* we had configured the Grok session with the desired sample rate.
 2026-01-16 15:41:33 -05:00
James Hush
1c13ad95a5 Fix Pylance reportOptionalMemberAccess in _handle_function_call_cancel 
Extract dictionary value to local variable and check for None before
accessing cancel_on_interruption attribute, since the dictionary values
are typed as Optional[FunctionCallInProgressFrame].
 2026-01-16 15:04:26 -05:00
Mark Backman
1e8516e91d Merge pull request #3476 from pipecat-ai/mb/project-urls 
Update project.urls for PyPI
 2026-01-16 14:57:39 -05:00
Mark Backman
32c775311d Merge pull request #3471 from pipecat-ai/mb/fix-pydantic-2.12-docs 
Revert pydantic 2.12 extra type annotation
 2026-01-16 14:57:24 -05:00
Mark Backman
28d0bb98de Merge pull request #3472 from pipecat-ai/mb/whisker-dev 
Add whisker_setup.py setup file to .gitignore
 2026-01-16 14:55:48 -05:00
Aleix Conchillo Flaqué
a9a9f3aeaa Merge pull request #3462 from pipecat-ai/aleix/fix-min-words-transcription-aggregation 
MinWordsUserTurnStartStrategy: don't aggregate transcriptions
 2026-01-16 11:18:23 -08:00
Aleix Conchillo Flaqué
c2a0735975 MinWordsUserTurnStartStrategy: don't aggregate transcriptions 
If we aggregate transcriptions we will get incorrect interruptions. For example,
if we have a strategy with min_words=3 and we say "One" and pause, then "Two"
and pause and then "Three", this would trigger the start of the turn when it
shouldn't. We should only look at the incoming transcription text and don't
aggregate it with the previous.
 2026-01-16 11:16:06 -08:00
Aleix Conchillo Flaqué
41cb53f6c2 Merge pull request #3479 from pipecat-ai/aleix/turns-mute-to-user-mute 
turns: move mute to user_mute
 2026-01-16 11:11:50 -08:00
Aleix Conchillo Flaqué
58552af8fd examples(foundational): remote STTMuteFilter example 2026-01-16 11:07:20 -08:00
Aleix Conchillo Flaqué
c7ab87b0cc turns: move mute to user_mute 2026-01-16 11:07:20 -08:00
Mark Backman
11ecc5fdee Update project.urls for PyPI 2026-01-16 12:48:13 -05:00
kompfner
19fb3eed9f Merge pull request #3466 from pipecat-ai/pk/fix-aws-nova-sonic-rtvi-bot-output 
Fix realtime (speech-to-speech) services' RTVI event compatibility
 2026-01-16 09:56:13 -05:00