Commit Graph

2747 Commits

Author SHA1 Message Date
richtermb
ead4e97ab5 Add source parameter to ErrorFrame and set it in FrameProcessor. Updated error handling in AnthropicLLMService and DeepgramSTTService to include ErrorFrame with source information. 2025-08-01 11:14:50 -07:00
Sam Sykes
7c223a86c2 Fix to missing deprecated attribute enable_speaker_diarization. 2025-07-31 22:25:46 +01:00
Sam Sykes
2d3f61aa07 Updated Speechmatics Plugin (#2225)
Changes
Split out module attributes to make engine settings clearer
Removed internal audio buffer to use latest Speechmatics python SDK (0.4.0)
Use diarization for improved VAD in multi-speaker situations
Support custom dictionary / vocabulary with attributes
Deprecated attributes superseded by re-organised attributes

Diarization Enhancements
Focus on specific speakers (using speaker labels)
Ignore specific speakers (using speaker labels)
Separate transcription formats for active and inactive speakers
Support for known speakers
2025-07-31 17:51:38 -03:00
Aleix Conchillo Flaqué
c2d8844903 Merge pull request #2312 from pipecat-ai/aleix/srhinos/main
Enable Interruption Support for LLMUserResponseAggregator
2025-07-31 13:30:57 -07:00
Aleix Conchillo Flaqué
7553f670af fix formatting and update CHANGELOG 2025-07-31 10:41:11 -07:00
Aleix Conchillo Flaqué
e78d9c2c95 Merge pull request #2293 from azain47/azain47/fix-piper-tts-service
Fix Piper TTS Service
2025-07-31 08:32:17 -07:00
Mark Backman
d692843e5b Merge pull request #2308 from pipecat-ai/mb/change-neuphonic-url
NeuphonicTTSService: change the default url value to the global endpoint
2025-07-31 07:38:57 -07:00
Mark Backman
eaad3c5d55 NeuphonicTTSService: change the default url value to the global endpoint 2025-07-31 10:24:54 -04:00
Vanessa Pyne
af8de227bb Merge pull request #2223 from getchannel/realtime-text
Add text input handling to unify context for realtimeInput stream of GeminiMultimodalLiveService
2025-07-31 08:53:39 -05:00
Mark Backman
aa85fffa57 New runner module (#2269)
* Adds pipecat.runner.run - FastAPI-based development server with automatic bot discovery

* Adds new RunnerArguments types for different transports

* Adds new runner utils for creating transports and parsing data

* Adds new Daily and LiveKit utils for setup
2025-07-30 22:02:28 -04:00
srhinos
8b97ab70ff Enable Interruption Support for LLMUserResponseAggregator 2025-07-30 20:48:31 -04:00
Filipi Fuchter
0c6e12a9b0 Fixed a race condition in FastAPIWebsocketClient that occurred when attempting to send a message while the client was disconnecting. 2025-07-30 18:07:40 -03:00
Filipi da Silva Fuchter
318ebec67e Merge pull request #2298 from pipecat-ai/filipi/google_interruptions
Fixed an issue in GoogleLLMService where interruptions did not work when an interruption strategy was used.
2025-07-30 17:49:07 -03:00
Filipi Fuchter
392853f5fa Fixed an issue in GoogleLLMService where interruptions did not work when an interruption strategy was used. 2025-07-30 12:10:32 -03:00
Mark Backman
0fa51968bf Added the ability to switch voices to RimeTTSService 2025-07-30 10:53:14 -04:00
Filipi Fuchter
6e921cdf45 HeyGen implementation for Pipecat - HeyGenVideoService 2025-07-30 09:07:15 -03:00
Azain.
1e2b066cf3 Fix tts.py
Update Piper TTS Service to work with the newer Piper GPL Version, that uses JSON as its payload.
2025-07-30 13:41:27 +05:30
Pete
2af3b6329d Ruff format debug 2025-07-29 17:48:11 -04:00
Pete
8ca06e5887 Add InputTextRawFrame class for handling raw text input in frames
- Introduced `InputTextRawFrame` to represent raw text input from users or programs.
- Updated `GeminiMultimodalLiveLLMService` to process `InputTextRawFrame` and send user text via the Gemini Live API's realtime input stream.
- Enhanced `_send_user_text` method documentation for clarity on its functionality and usage.
2025-07-29 17:43:14 -04:00
Mark Backman
c145a9ef13 Merge pull request #2288 from pipecat-ai/mb/stt-mute-examples
Update placement of STTMuteFilter in examples to reflect the new reco…
2025-07-29 12:10:36 -07:00
Mark Backman
7f184422d0 Merge branch 'main' into feat/async-tts 2025-07-29 12:06:56 -07:00
Aleix Conchillo Flaqué
fa4c3ec6bf Merge pull request #2287 from pipecat-ai/aleix/asyncio-trace-logging
utils(asyncio): use trace logging for some cancelling messages
2025-07-29 11:56:25 -07:00
richtermb
67107d02ed Refactor callback invocation for on_transcription_stopped in DailyTransportClient for improved readability 2025-07-29 11:53:41 -07:00
richtermb
c1df19982c Add on_transcription_stopped callback to DailyTransport for handling transcription stop events 2025-07-29 11:50:16 -07:00
richtermb
444b1b5b02 Add on_transcription_stopped callback to DailyCallbacks and implement handling in DailyTransport for transcription stop events 2025-07-29 11:49:28 -07:00
Mark Backman
ebfa4f2d5e Push the STTMuteFrame upstream and downstream 2025-07-29 14:37:36 -04:00
richtermb
d3d36a89e2 Add _on_transcription_error method to DailyTransport for handling transcription error events 2025-07-29 10:48:50 -07:00
richtermb
fa6e5ce4a7 Add on_transcription_error callback to DailyCallbacks and handle transcription errors in DailyTransportClient 2025-07-29 10:43:18 -07:00
Ashot
39b00f5269 chore: address review comments 2025-07-29 18:20:50 +04:00
Tomoaki Imai
3ae8cf1916 Add transcription_bucket param for rest helper 2025-07-29 18:58:38 +09:00
Aleix Conchillo Flaqué
03e87469df utils(asyncio): use trace logging for some cancelling messages 2025-07-28 17:43:41 -07:00
Mark Backman
96a72d0647 Remove message[name] addition when pushing 2025-07-28 20:13:50 -04:00
Mark Backman
50242f4ad8 fix: Improve TranscriptProcessor detection for transcript type 2025-07-28 19:56:36 -04:00
Ashot
83b4747196 chore: address review comments 2025-07-28 17:52:17 +04:00
Ashot
a13b954415 formatting/cleanup: address Copilot PR review comments 2025-07-28 17:43:17 +04:00
Ashot
f2e9562f1b feat(tts): integrate Async TTS engine into pipecat 2025-07-28 17:42:57 +04:00
Filipi da Silva Fuchter
9d5510ee47 Merge pull request #2265 from pipecat-ai/filipi/small_webrtc_buffer_processor
Fixed an issue in AudioBufferProcessor when using SmallWebRTCTransport
2025-07-28 09:23:58 -03:00
Mark Backman
41c8d22cf3 Merge pull request #2208 from padillamt/mtp/add-inworld-tts
Inworld HTTP TTS Service
2025-07-25 17:13:37 -07:00
padillamt
e140bd6960 mtpadilla: moved model and voice id setting into the class constructor 2025-07-25 14:04:49 -07:00
Filipi Fuchter
e86b55e2b3 Fixed an issue in AudioBufferProcessor when using SmallWebRTCTransport where, if the microphone was muted, track timing was not respected. 2025-07-25 17:01:41 -03:00
padillamt
4a9bec5b35 mtpadilla: stop metrics at result chunk 2025-07-25 11:14:20 -07:00
padillamt
37361391d9 mtpadilla: removed ability to set base_url via constructor, set internally based on streaming variable 2025-07-25 09:16:56 -07:00
Filipi da Silva Fuchter
4b3726eba4 Merge pull request #2260 from pipecat-ai/filipi/audio_resampler
Fixed an issue in `AudioBufferProcessor` that caused garbled audio
2025-07-25 09:27:42 -03:00
padillamt
acc5b9f210 inworld: change to function that stops all processing metrics
Co-authored-by: Mark Backman <m.backman@gmail.com>
2025-07-24 22:07:15 -07:00
padillamt
5fb1899aeb inworld: removal of unnecessary default assignment as already handled 2025-07-24 21:42:42 -07:00
padillamt
7483422bd9 inworld: change set_voice uto use self._settings
Co-authored-by: Mark Backman <m.backman@gmail.com>
2025-07-24 21:23:03 -07:00
padillamt
16c20f3a99 inworld: removal of unnecessary default assignment since already done
Co-authored-by: Mark Backman <m.backman@gmail.com>
2025-07-24 21:15:34 -07:00
padillamt
d248c102c8 inworld: removal of unnecessary default assignment since already done
Co-authored-by: Mark Backman <m.backman@gmail.com>
2025-07-24 21:15:20 -07:00
padillamt
662550cc5e mtpadilla: remove unused imports 2025-07-24 21:05:22 -07:00
padillamt
067f64389b mtpadilla: no longer needed so making empty 2025-07-24 20:44:27 -07:00