wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
6,903 Commits 276 Branches 111 Tags
95f00a3c4bea3f51c9260b47efdc6df5c43376b2
Commit Graph

6903 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Mark Backman
95f00a3c4b AzureTTSService: Align error handling with Pipecat norms 2026-01-07 15:45:30 -05:00
Mark Backman
3f8373f76f AzureTTSService: prevent word timestamp carryover on interruption 2026-01-07 15:39:37 -05:00
Mark Backman
23a9d3f4d7 Merge pull request #3334 from obata-kotobasamurai/fix/azure-tts-word-timestamp 
Add word-level timestamp support to Azure TTS with race condition fix
 2026-01-07 14:48:02 -05:00
Mark Backman
333279f45a Merge pull request #3328 from speechmatics/fix/speectmatics-vad 
Update to SpeechmaticsSTTService for `0.0.99`
 2026-01-07 14:42:21 -05:00
yukiobata1
add5f51201 updated azure tts.py file 2026-01-08 03:14:37 +09:00
Mark Backman
54cf0116a8 Merge pull request #3363 from pipecat-ai/mb/update-audo-context-inheritance 
Update AudioContextTTSService to inherit from WebsocketTTSService
 2026-01-07 12:08:47 -05:00
Sam Sykes
3e00a16f0f Remove unused import and correction to docs. 2026-01-07 07:45:26 -08:00
Sam Sykes
ecfd93544a Correction to UserStartedSpeakingFrame timing. 2026-01-07 07:43:47 -08:00
Sam Sykes
3ec89e49bf Added changelog for split_sentences and code tidy for end of turn handling. 2026-01-07 07:41:49 -08:00
Mark Backman
8762506e9f Update AudioContextTTSService to inherit from WebsocketTTSService 2026-01-07 09:10:27 -05:00
yukiobata1
7204bf9914 added changegelog 2026-01-07 13:32:31 +09:00
yukiobata1
f62c262f23 Call start_word_timestamps() when the first audio chunk arrives 2026-01-07 13:10:41 +09:00
Mark Backman
10aa784809 Merge pull request #3351 from okue/fix/stt-model-name-attribute 
Fix STT model name attribute retrieval in tracing decorator
 2026-01-06 16:10:56 -05:00
Filipi da Silva Fuchter
904f5dc183 Merge pull request #3338 from omChauhanDev/fix/smallwebrtc-mute-timeout-spam 
fix(smallwebrtc): suppress timeout warnings when tracks are disabled
 2026-01-06 09:07:52 -05:00
Mark Backman
c61a5e7173 Merge pull request #3346 from pipecat-ai/mb/cartesia-pronunciation-dict 
Cartesia TTS: Add support for pronunciation_dict_id
 2026-01-06 08:52:09 -05:00
Filipi da Silva Fuchter
81b28beef5 Merge pull request #3357 from pipecat-ai/filipi/live_avatar 
Added support for using the HeyGen LiveAvatar API with the HeyGenTransport
 2026-01-06 08:22:39 -05:00
filipi87
0d34356678 Adding a changelog entry for the HeyGen LiveAvatar API change. 2026-01-06 10:19:19 -03:00
filipi87
5412840a93 Added support for using the HeyGen LiveAvatar API with the HeyGenTransport. 2026-01-06 10:16:12 -03:00
yukiobata1
137bbb3d2c updated tts.py to match mark's version 2026-01-06 21:16:13 +09:00
Mark Backman
5a40054ac2 Merge pull request #3216 from mayurdd/patch-1 
Adding include_language_detection param to Elevenlabs Realtime STT
 2026-01-05 17:01:02 -05:00
Mark Backman
9ab4836601 Merge pull request #3323 from pipecat-ai/mb/changelog-3322 
Add changelog fragment for PR #3322
 2026-01-05 16:55:52 -05:00
mayurdd
4671102833 Addressing the comments 2026-01-05 13:35:37 -08:00
Mayur Sirwani
67401a275b Adding include_language_detection to Elevenlabs Realtime STT 
Adding a param to the config while connecting to the session
 2026-01-05 13:27:27 -08:00
Mark Backman
c422588071 Merge pull request #3345 from pipecat-ai/mb/avoid-tts-dot 
Add trailing space to DeepgramTTSService text generation
 2026-01-05 15:56:14 -05:00
kompfner
fb12fec899 Merge pull request #3354 from pipecat-ai/pk/fix-aws-nova-sonic-example-for-nova-2-sonic 
Fix the 20e example to use the proper conversation-start pattern for …
 2026-01-05 11:17:57 -05:00
Paul Kompfner
c53c49558f Fix the 20e example to use the proper conversation-start pattern for the Nova 2 Sonic model 2026-01-05 10:56:08 -05:00
okue
1a26a2daa4 Fix STT model name attribute retrieval in tracing decorator 
Changed getattr with default value to use 'or' operator for fallback.
This ensures proper model name retrieval when model_name attribute exists but is None or empty.
 2026-01-05 17:20:48 +09:00
Mark Backman
d8be1282b5 Cartesia TTS: Add support for pronunciation_dict_id 2026-01-04 09:30:04 -05:00
Mark Backman
91bc5236b5 Add trailing space to DeepgramTTSService text generation 2026-01-04 08:53:48 -05:00
Mark Backman
1c80c739d6 Merge pull request #3335 from pipecat-ai/mb/update-evals-07-variants 
Add 07 example variants to release evals
 2026-01-02 15:32:12 -05:00
Om Chauhan
700a94222b fix(smallwebrtc): suppress timeout warnings when tracks are disabled 2026-01-01 22:00:08 +05:30
Sam Sykes
d5d2156689 Updated changelog. 2025-12-31 19:07:11 +00:00
Sam Sykes
8203ad08a8 Updated to have default as FIXED for Pipecat VAD. 2025-12-31 19:05:29 +00:00
Mark Backman
31907b90f0 Add 07 example variants to release evals 2025-12-31 09:11:00 -05:00
Mark Backman
7b595f10ce Merge pull request #3329 from omChauhanDev/deepgram-tts-validation 
added encoding validation in DeepgramTTSService
 2025-12-31 08:20:40 -05:00
yukiobata1
4f93d331b7 Added await to self.start_word_timestamps() 2025-12-31 19:19:21 +09:00
yukiobata1
32c6dccebe Add word-level timestamp support to Azure TTS with cumulative PTS fix 
This commit adds word boundary support to AzureTTSService and fixes
the race condition that causes scrambled TTS output across multiple
sentences.

## Features Added

- Change AzureTTSService to inherit from WordTTSService
- Subscribe to Azure SDK's synthesis_word_boundary event
- Emit word-level text with timing information via _words_queue
- Add synthesis lock for sequential sentence processing

## Race Condition Fix

Previously, each sentence's word boundary timestamps reset to 0,
causing downstream components to interleave words when reordering
frames by PTS. This resulted in scrambled output like:
  'Hello ! I What am questions AI have assistant...'

The fix adds cumulative audio offset tracking to ensure monotonically
increasing PTS across all sentences:
  Sentence 1: pts = 0.1s, 0.5s, 0.8s (cumulative at end: 0.8s)
  Sentence 2: pts = 0.9s, 1.2s, 1.5s (0.8s + relative offset)

## Key Changes

- _cumulative_audio_offset: tracks total audio duration
- _handle_word_boundary: adds cumulative offset to timestamps
- _handle_completed: accumulates audio duration for next sentence
- flush_audio: resets cumulative offset at end of LLM response
- _handle_interruption: resets state on user interruption
- run_tts: uses synthesis lock for sequential processing

Fixes #2918

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
 2025-12-31 18:49:48 +09:00
Aleix Conchillo Flaqué
cbdc2b7d2d Merge pull request #3330 from pipecat-ai/aleix/update-turn-start-strategies-deprecations 
update turn start strategies deprecations
 2025-12-30 21:04:47 -08:00
Aleix Conchillo Flaqué
66a9dc70c7 LLMUserAggregator: fix turn strategies renaming 2025-12-30 20:59:48 -08:00
Aleix Conchillo Flaqué
846ca500d3 turns: update old turn_start_strategies deprecations 2025-12-30 19:50:10 -08:00
Om Chauhan
bd6afd445d added changelog 2025-12-31 09:18:18 +05:30
Om Chauhan
0663bbc2fb added encoding validation in DeepgramTTSService 2025-12-31 08:33:17 +05:30
Sam Sykes
8e7a951af8 updated changelog 2025-12-31 01:36:58 +00:00
Sam Sykes
ba1aeb8f7f Changelog 2025-12-31 01:31:46 +00:00
Sam Sykes
f7c74cfa80 Updated VAD 2025-12-31 01:28:31 +00:00
Mark Backman
2e700c8576 Merge pull request #3324 from pipecat-ai/mb/bump-small-webrtc-prebuilt-version 
Bump small-webrtc-prebuilt verison to 2.0.4, update uv.lock
 2025-12-30 20:10:11 -05:00
Aleix Conchillo Flaqué
fd2efb3b3a Merge pull request #3325 from pipecat-ai/aleix/rename-bot-turn-start-to-user-turn-stop 
turns: rename bot turn start to user turn stop strategies
 2025-12-30 14:36:02 -08:00
Aleix Conchillo Flaqué
eb5a797b12 turns: rename bot turn start to user turn stop strategies 2025-12-30 14:33:58 -08:00
Mark Backman
f4626a4fc4 Bump small-webrtc-prebuilt verison to 2.0.4, update uv.lock 2025-12-30 14:19:20 -05:00
Aleix Conchillo Flaqué
fb9a772e33 Merge pull request #3319 from pipecat-ai/aleix/openaillmcontext-backwards-compatibility 
BaseInputTransport: fix OpenAILLMContext backwards compatibility
 2025-12-30 09:35:43 -08:00