Commit Graph

3967 Commits

Author SHA1 Message Date
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
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
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
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
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
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
Om Chauhan
700a94222b fix(smallwebrtc): suppress timeout warnings when tracks are disabled 2026-01-01 22:00:08 +05:30
Sam Sykes
8203ad08a8 Updated to have default as FIXED for Pipecat VAD. 2025-12-31 19:05:29 +00:00
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
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
0663bbc2fb added encoding validation in DeepgramTTSService 2025-12-31 08:33:17 +05:30
Sam Sykes
f7c74cfa80 Updated VAD 2025-12-31 01:28:31 +00:00
Aleix Conchillo Flaqué
eb5a797b12 turns: rename bot turn start to user turn stop strategies 2025-12-30 14:33:58 -08:00
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
Aleix Conchillo Flaqué
4630e76942 ExternalUserTurnStartStrategy: disable interruptions 2025-12-30 09:32:31 -08:00
Aleix Conchillo Flaqué
4dba9ea329 BaseInputTransport: fix OpenAILLMContext backwards compatibility 2025-12-30 09:32:31 -08:00
Mark Backman
9c6d0f1be1 Merge pull request #3322 from gui217/fix/rnnoise_filter_handle_empty_audio
Fix/rnnoise filter handle empty audio
2025-12-30 08:39:42 -05:00
gui217
bad8f8aa51 Fix rnnoise filter to handle empty audio 2025-12-30 13:32:36 +02:00
Aleix Conchillo Flaqué
0a0ab51cc7 LLMUserAggregator: also read deprecated allow_interruptions 2025-12-29 17:57:18 -08:00
Aleix Conchillo Flaqué
ad4c22cf44 Merge pull request #3316 from pipecat-ai/aleix/llm-user-aggreagtor-enable-interruptions
turns(user): add support for enabling/disabling interruptions
2025-12-29 17:45:56 -08:00
Aleix Conchillo Flaqué
9fe99ed880 add and update changelog entries 2025-12-29 17:35:10 -08:00
Aleix Conchillo Flaqué
ffbbb1b3f5 turns(user): add support for enabling/disabling interruptions 2025-12-29 17:00:03 -08:00
Aleix Conchillo Flaqué
e22a6c9e4d Merge pull request #3305 from omChauhanDev/fix_unregister_function
fix: missing key access by adding existence check
2025-12-29 14:52:41 -08:00
Aleix Conchillo Flaqué
09e79149ea Merge pull request #3310 from omChauhanDev/fix-task-manager
fix: preserve asyncio.Task return value in create_task
2025-12-29 14:43:24 -08:00
Aleix Conchillo Flaqué
bd9a316d7a transports: don't use interruptions_allowed to avoid deprecation warning 2025-12-29 14:40:00 -08:00
Aleix Conchillo Flaqué
c8f47b4b22 turns: add UserTurnStartedParams and BotTurnStartedParams 2025-12-29 14:32:08 -08:00
Mark Backman
c28ed2206c DeepgramSTTService pushes user started/stopped speaking and interruption frames 2025-12-29 10:17:35 -08:00
Mark Backman
30e6a33930 Update VoicemailDetector to use ExternalTurnStartStrategies 2025-12-29 10:17:35 -08:00
Aleix Conchillo Flaqué
46db8e58d6 LLMUserAggregator: fix backwards compatibility with ExternalTurnStartStrategies 2025-12-29 10:17:35 -08:00
Aleix Conchillo Flaqué
c821e9f8fd turns: add external user and bot turn start strategies
External strategies are strategies where the logic for user turn start and turn
end come from a different processors (e.g. an STT).
2025-12-29 10:17:35 -08:00
Mark Backman
01ce06c756 Merge pull request #3288 from pipecat-ai/mb/inworld-cleanup
Inworld TTS service clean up
2025-12-29 13:07:20 -05:00
Mark Backman
4bc490c843 Merge pull request #3289 from pipecat-ai/mb/audio-context-tts-service-base
Add AudioContextTTSService base class, update AudioContextWordTTSServ…
2025-12-29 13:05:06 -05:00
Mark Backman
7c0d897aa3 Merge pull request #3300 from omChauhanDev/nvidia-expose-use_ssl-param
exposed use_ssl param in nvidia services
2025-12-29 09:18:26 -05:00
Aleix Conchillo Flaqué
0e8e3afc85 Merge pull request #3307 from pipecat-ai/aleix/simplify-turns-package-imports
turns: simplify imports and don't require full strategy module path
2025-12-28 18:51:23 -08:00
Om Chauhan
a181e01310 fixed: create_task to return coroutine result 2025-12-29 07:46:15 +05:30