Aleix Conchillo Flaqué
21e4f0d56d
PipelineRunner: argument ordering
2025-08-05 14:38:55 -07:00
Aleix Conchillo Flaqué
627b44bac2
runner: use new RunnerArguments handle_sigint/handle_sigterm
...
This allow us to control applications behavior from the runner arguments, which
depen on the environment they run.
2025-08-05 14:38:55 -07:00
Aleix Conchillo Flaqué
e2a576beca
RunnerArguments: add handle_sigint/handle_sigterm
2025-08-05 14:32:28 -07:00
Mark Backman
d422c57b52
Merge pull request #2304 from pipecat-ai/mb/cartesia-cjk-lang-support
...
CartesiaTTSService: Add CJK lang support for word timestamps
2025-08-05 14:08:53 -07:00
Mark Backman
a0e2a2754a
Merge pull request #2327 from richtermb/richtermb/push-more-error-frames
...
Add source parameter to ErrorFrame and set it in FrameProcessor. Upda…
2025-08-05 14:04:52 -07:00
Mark Backman
b8d620c8bb
Merge pull request #2362 from pipecat-ai/mb/aws-stt-languages
...
AWSTranscribeSTTService add support for new languages
2025-08-05 14:00:50 -07:00
Mark Backman
52cb23f8d5
Merge pull request #2364 from pipecat-ai/mb/11labs-default-model
...
ElevenLabs TTS services: revert to Turbo v2.5 as default model
2025-08-05 13:59:59 -07:00
Filipi da Silva Fuchter
17e7f8a2cd
Merge pull request #2352 from pipecat-ai/filipi/webrtc_audio_frame
...
Implementing if the bot it is speaking or not based on the SpeechOutputAudioRawFrame
2025-08-05 17:26:44 -03:00
richtermb
efddc4732c
Refactor ErrorFrame: rename source field to processor for clarity and update related references in FrameProcessor.
2025-08-05 13:25:08 -07:00
richtermb
4476a76ad7
Merge branch 'main' into richtermb/push-more-error-frames
2025-08-05 13:23:24 -07:00
Filipi Fuchter
64592b274b
Fixed an issue where BotStartedSpeakingFrame and BotStoppedSpeakingFrame
...
were not emitted when using `TavusVideoService` or `HeyGenVideoService`.
2025-08-05 17:11:34 -03:00
Mark Backman
14e02c1b08
ElevenLabs TTS services: revert to Turbo v2.5 as default model
2025-08-05 13:44:37 -04:00
Mark Backman
2378cba155
AWSTranscribeSTTService add support for new languages
2025-08-05 13:01:06 -04:00
Mark Backman
1138c92a00
Merge pull request #2217 from simliai/main
...
feat: Add Simli Trinity models support to pipecat
2025-08-05 09:01:20 -07:00
Mark Backman
64732518c6
Development runner handles body information in the RTVI connect request
2025-08-05 07:26:34 -04:00
Mark Backman
c3d8ea210f
CartesiaTTSService: Add CJK lang support for word timestamps
2025-08-05 07:17:40 -04:00
Filipi Fuchter
e43bdff31e
Added detailed latency logging to UserBotLatencyLogObserver.
2025-08-04 19:36:30 -03:00
Mark Backman
ac9b2e67a7
Merge pull request #2349 from pipecat-ai/mb/runner-support-daily-url-arg
...
daily runner util: remove arg parsing, add auto room, token generation
2025-08-04 13:44:25 -07:00
Mark Backman
c9918607cf
Merge pull request #2335 from pipecat-ai/mb/quickstart-runner-improvements
...
Improve quickstart logging, runner startup message
2025-08-04 13:43:42 -07:00
Mark Backman
3a8d809837
Runner: strip protocol from proxy address
2025-08-04 13:38:02 -04:00
Vanessa Pyne
96b1000e52
Merge pull request #2341 from getchannel/realtime-text
...
Hotfix: Correct Gemini Live API class to fix 1007 payload error.
2025-08-04 11:03:57 -05:00
Filipi da Silva Fuchter
0184a8c231
Merge pull request #2351 from pipecat-ai/filipi/tavus_transport_ready
...
Changed `TavusVideoService` to send audio or video frames only after the transport is ready, preventing warning messages at startup.
2025-08-04 11:48:27 -03:00
Filipi Fuchter
0e533d21be
Only send audio and video from the tavus video service if the transport is ready.
2025-08-04 10:52:30 -03:00
Mark Backman
6f6f4c3dea
Merge pull request #2348 from sam-s10s/speechmatics-stt
...
Fix for Speechmatics STT
2025-08-04 06:15:39 -07:00
Mark Backman
f609971637
daily runner util: remove arg parsing, add auto room, token generation
2025-08-03 21:50:44 -04:00
Mark Backman
54ff10ae86
Merge pull request #2332 from hankehly/fix-piper-tts-json-payload
...
Fix PiperTTSService to send TTS input as JSON object
2025-08-03 17:39:04 -07:00
hankehly
77057eb829
Fix ruff formatting
2025-08-04 08:13:16 +09:00
Sam Sykes
c2282b0e73
Set user_id to "" (not None) for RTVIProcessor.
2025-08-03 22:08:22 +01:00
Aleix Conchillo Flaqué
3a72e94d0c
LLMService: only do handle function inspection once
2025-08-03 10:09:19 -07:00
Aleix Conchillo Flaqué
d6d39fc873
TaskObserver: don't inspect on_push_frame signature for every frame
2025-08-03 10:09:17 -07:00
Pete
258e83c904
Fix: Correct Gemini Live API text input to prevent 1007 WebSocket errors
...
- Restore TextInputMessage.realtimeInput structure for correct API format
- Remove invalid turnComplete message from _send_user_text method
- turnComplete is only valid for clientContent, not realtimeInput messages
- realtimeInput text completion is automatically inferred by the API
This fixes WebSocket 1007 errors caused by mixing realtimeInput and
clientContent message types in violation of the Gemini Live API contract.
2025-08-03 10:58:59 -04:00
Mark Backman
e467eaf130
Merge pull request #2334 from Designedforusers/fix/tavus-transport-daily-callbacks
...
fix: Add missing transcription callbacks to TavusTransport for 0.0.77 compatibility
2025-08-02 16:09:57 -07:00
Designedforusers
9d6d53629e
style: Apply ruff formatting to fix line length
...
Fixed a line length issue in tavus.py where the on_transcription_stopped callback was exceeding the maximum line length. Split the partial() call across multiple lines for better readability and compliance with project style guidelines.
2025-08-02 18:27:09 -04:00
Designedforusers
5e338ecaf1
refactor: Remove redundant transcription callback methods
...
As suggested in PR review, removed the _on_transcription_stopped and
_on_transcription_error method definitions. Now using the consistent
partial(self._on_handle_callback, ...) pattern for these callbacks,
matching how all other callbacks are handled.
This simplifies the code while maintaining the same functionality.
2025-08-02 15:02:54 -04:00
Pete
cccd82a617
Refactor TextInputMessage class to replace realtimeInput with a text attribute.
...
This was sending a 1007 because it was wrapping RealtimeInput in the json.
- Updated the `TextInputMessage` class to directly store text input as a string.
- Modified the `from_text` class method to create an instance using the new `text` attribute.
2025-08-02 14:34:00 -04:00
Mark Backman
e43b3869c3
Suppress pydub SyntaxWarning from the cartesia module
2025-08-02 08:49:59 -04:00
Mark Backman
55731df999
Improve quickstart logging, runner startup message
2025-08-02 08:40:05 -04:00
Designedforusers
3a7ea25077
fix: Add missing transcription callbacks to TavusTransport for 0.0.77 compatibility
...
TavusTransport was broken in Pipecat 0.0.77 due to PR #2292 adding required
callbacks (on_transcription_stopped, on_transcription_error) to DailyCallbacks.
This fix adds placeholder implementations of these callbacks to TavusTransportClient,
allowing TavusTransport to initialize properly. These callbacks are not used by
Tavus (which handles avatar video, not transcription) but are required by the
DailyCallbacks validation.
Fixes initialization error:
- 2 validation errors for DailyCallbacks
- on_transcription_stopped: Field required
- on_transcription_error: Field required
2025-08-02 05:56:46 -04:00
Yohan Liyanage
248206e234
Fixes 2277 - SSML reserved characters in LLM generated text causes Azure TTS to fail.
2025-08-02 12:49:29 +05:30
hankehly
694922f627
Fix PiperTTSService to send TTS input as JSON object
2025-08-02 15:29:16 +09:00
Richter Brzeski
c2d05ad23b
Merge branch 'pipecat-ai:main' into richtermb/push-more-error-frames
2025-08-01 14:47:08 -07:00
richtermb
91568eeddc
Update type hint for source in ErrorFrame to use forward declaration for improved clarity.
2025-08-01 12:52:56 -07:00
Mark Backman
1d8abe3c1c
fix: LiveKitTransport, don't push empty AudioRawFrames
2025-08-01 14:57:53 -04:00
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
Mark Backman
ff45b77fdf
Remove examples runner
2025-07-31 21:22:04 -04:00
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
