Aleix Conchillo Flaqué
b118082984
AudioBufferProcessor: treat all streams as intermittent
...
This fixes an issue with STTMuteFilter that prevents user audio to be pushed
downstream.
2025-06-18 18:23:31 -07:00
Filipi da Silva Fuchter
171597fbe9
Merge pull request #1952 from jqueguiner/feat/gladia-auto-reconnect
...
feat: Enhance GladiaSTTService with reconnection and audio buffer management features
2025-06-18 16:14:58 -03:00
Mark Backman
e5b7dbba90
fix: ElevenLabsTTSService voice settings not being sent
2025-06-18 09:49:17 -04:00
Filipi Fuchter
8b4a86f629
Ignoring the audio level when creating the custom tracks.
2025-06-18 07:45:54 -03:00
Filipi Fuchter
564f064c71
Refactoring TavusVideoService to send audio using WebRTC audio tracks instead of app-messages.
2025-06-18 07:44:51 -03:00
Filipi Fuchter
4062c7afa0
Refactoring TavusTransport to send audio using WebRTC audio tracks instead of app-messages.
2025-06-18 07:44:38 -03:00
Jean-Louis Queguiner
8071c4ba1c
Merge branch 'main' into feat/gladia-auto-reconnect
2025-06-18 08:57:21 +02:00
jqueguiner
3d0ffbc832
🐛 (stt.py): handle websocket connection closure gracefully and log warnings
...
♻️ (stt.py): refactor reconnection logic into a separate method for clarity
✨ (stt.py): implement exponential backoff for reconnection attempts to improve reliability
2025-06-18 08:52:43 +02:00
Aleix Conchillo Flaqué
c11172caba
examples: create transport params async
2025-06-17 11:37:42 -07:00
Aleix Conchillo Flaqué
4abf41b85a
Merge pull request #2011 from wuodar/wuodar/polish-lang-aws-transcribe
...
Support polish language in Amazon Transcribe
2025-06-16 10:33:55 -07:00
Aleix Conchillo Flaqué
14dc6a7984
FrameProcessor: handle new FrameProcessorPauseFrame/FrameProcessorResumeFrame
2025-06-16 10:31:33 -07:00
Mark Backman
d1bee22d73
Expose has_function_calls_in_progress property
2025-06-16 12:45:16 -04:00
Kacper Włodarczyk
e2c15169b8
feat: support polish language in Amazon Transcribe
2025-06-15 21:44:06 +02:00
Kwindla Hultman Kramer
1e3fa4a9c7
fix groq wav file header parsing
2025-06-14 17:41:44 -04:00
Filipi Fuchter
1f072d182c
Merge branch 'main' into filipi/google_stt_reconnection_issue
...
# Conflicts:
# CHANGELOG.md
2025-06-13 08:26:00 -03:00
Mark Backman
69c63293fb
fix: GoogleLLMService TTFB value
2025-06-12 11:43:27 -04:00
Filipi Fuchter
c1db13ceeb
Fixed an issue with GoogleSTTService where it was constantly reconnecting before starting to receive audio from the user.
2025-06-12 12:07:33 -03:00
Sunah Suh
d3df75aaa0
Add additional_span_attributes param to PipelineTask for extra otel… ( #1992 )
2025-06-10 17:32:24 -04:00
Mark Backman
257dbe3104
Fix model param error
2025-06-10 15:14:47 -04:00
Mark Backman
0bb61d72ab
Merge pull request #1984 from pipecat-ai/mb/cartesia-stt-cleanup
...
CartesiaSTTService cleanup
2025-06-10 10:30:18 -04:00
Mark Backman
69d0218d7e
Add languages to RimeHttpTTSService, extend lang support to German and French
2025-06-10 10:20:41 -04:00
Aleix Conchillo Flaqué
093697906c
Merge pull request #1954 from WebinarGeek/wg/gladia-informal-translations
...
Gladia informal translations
2025-06-09 20:21:40 -07:00
Mark Backman
aec70d61e9
CartesiaSTTService cleanup
2025-06-09 15:20:57 -04:00
Mark Backman
15aeb11c36
Resample audio in ExotelFrameSerializer
2025-06-09 14:02:25 -04:00
Mark Backman
e705f4d984
Merge pull request #1972 from Vaibhav159/vl_add_exotel_serializer
...
adding exotel serializer
2025-06-09 13:54:26 -04:00
Shrey Gupta
96fa62fdfe
[Add] Support for Cartesia AI STT ( #1982 )
2025-06-09 14:51:01 -03:00
Mark Backman
845c70797a
Merge pull request #1975 from pipecat-ai/mb/11labs-flush-context-reset
...
fix: ElevenLabsTTSService reset context when flushing audio
2025-06-09 13:21:25 -04:00
kompfner
16048956c3
Merge pull request #1956 from pipecat-ai/pk/make-add-observer-sync
...
Make `PipelineTask.add_observer()` synchronous. This allows callers t…
2025-06-09 13:19:34 -04:00
Mark Backman
cf2f4b5902
fix: ElevenLabsTTSService reset context when flushing audio
2025-06-09 13:17:55 -04:00
Paul Kompfner
1cd96f94ff
Make PipelineTask.add_observer() synchronous. This allows callers to call it before run()ning the PipelineTask first. Without this change, if they tried to do that, they would get an error because the TaskManager's event loop hadn't been set yet.
2025-06-09 11:30:24 -04:00
Aleix Conchillo Flaqué
901dd041f0
buffer audio from TTS service before pushing frames
2025-06-09 07:29:09 -07:00
Vaibhav159
a2ee94651e
removing resampling
2025-06-07 12:53:55 +05:30
Aleix Conchillo Flaqué
a33ce5e4bf
AssemblyAISTTService: yield None instead of Frame()
2025-06-06 14:41:01 -07:00
Filipi Fuchter
028650249c
Adding support in ProtobufFrameSerializer to deserialize MessageFrame.
2025-06-06 17:07:39 -03:00
Vaibhav159
d2f4bb574c
adding exotel serializer
2025-06-07 00:22:41 +05:30
jqueguiner
25ff8ef37b
✨ (config.py): add new configuration options for lip-sync optimization, context adaptation, and additional context to enhance translation accuracy
...
♻️ (stt.py): increase default max buffer size from 5MB to 20MB to accommodate larger audio data
♻️ (stt.py): simplify audio sending logic by removing chunking and sending the entire buffered audio at once for improved performance
2025-06-05 16:51:29 -07:00
Aleix Conchillo Flaqué
581b800c43
Merge pull request #1961 from ken-kuro/patch-1
...
fix(piper-tts): typo
2025-06-05 12:57:58 -07:00
Aleix Conchillo Flaqué
30ca39287f
Merge pull request #1962 from ken-kuro/patch-2
...
fix(fastapi_websocket): typo
2025-06-05 12:57:22 -07:00
Kendrick Ha
f7761f2b61
fix(fastapi_websocket): typo
2025-06-05 13:55:28 +07:00
Kendrick Ha
49ff38a21f
fix(piper-tts): typo
2025-06-05 13:50:56 +07:00
Aleix Conchillo Flaqué
8d161306c7
disable uvloop by default and just let the user set it
2025-06-04 21:25:06 -07:00
vipyne
cb409d58e0
fix: transports/services/livekit.py typo
2025-06-04 11:14:21 -05:00
Dan Berg
094e2f8151
Fix formatting
2025-06-03 17:21:51 +02:00
Dan Berg
b1a88af43c
Add informal to Gladia TranslationConfig
2025-06-03 17:10:52 +02:00
Filipi Fuchter
31ca9be299
Fixing missing await to self.reset.
2025-06-03 08:37:47 -03:00
jqueguiner
02cc6f3d56
Enhance GladiaSTTService with reconnection and audio buffer management features
...
- Added parameters for maximum reconnection attempts, reconnection delay, and maximum audio buffer size.
- Implemented automatic reconnection logic with exponential backoff.
- Introduced audio buffer management to handle audio data efficiently, including trimming excess data.
- Updated connection handling to ensure proper cleanup and management of WebSocket connections.
- Enhanced audio sending logic to support buffered audio transmission after reconnections.
2025-06-03 03:16:57 -07:00
Filipi Fuchter
892d213442
Fixing issue to keep the transport_destination.
2025-06-02 22:16:10 -03:00
Filipi Fuchter
fc24267e09
Waiting for the LLM response to reset.
2025-06-02 22:15:53 -03:00
Aleix Conchillo Flaqué
532767cfa1
LLMUserContextAggregator: reset strategies when reseting the aggregator
2025-06-02 12:01:26 -07:00
Aleix Conchillo Flaqué
5512de3221
allow custom interruption strategies
2025-06-02 12:01:26 -07:00
