3688 Commits

Author	SHA1	Message	Date
Mark Backman	61da6437ea	Merge pull request #1834 from pipecat-ai/mb/gemini-live-tokens ... Fix: Make LLMTokenUsage more robust	2025-05-19 09:04:07 -04:00
Mark Backman	144ea36c81	Fix: Make LLMTokenUsage more robust	2025-05-18 07:41:16 -04:00
Jin Kim	a4c04e7c17	Opt out Sonic models from use_original_timestamps	2025-05-18 16:52:37 +09:00
Jin Kim	a6f7e7fc30	Merge branch 'pipecat-ai:main' into main	2025-05-18 16:48:24 +09:00
Aleix Conchillo Flaqué	d5ebc883b3	PipelineTask: add new started/stopped/ended/cancelled events	2025-05-17 22:46:22 -07:00
Mark Backman	deb43df0a4	Merge pull request #1824 from pipecat-ai/mb/gemini-live-transcribe-user-audio ... Update GeminiMultimodalLiveLLMService to use Gemini's user transcription	2025-05-16 22:51:04 -04:00
Mark Backman	f59fb8167d	Merge pull request #1784 from thsunkid/thu/handle-transcript-gpt4o-audio ... Handle audio transcript from gpt-4o-audio and clean up logs	2025-05-16 13:20:16 -04:00
Mark Backman	fac6f526f7	Add comments and docstrings	2025-05-16 10:54:50 -04:00
Mark Backman	2f78d74ce6	Change Gemini Live to use Gemini provided usage metrics	2025-05-16 10:53:01 -04:00
Mark Backman	d3942dda52	Gemini Live to transcribe user audio	2025-05-16 10:53:01 -04:00
kaikato	c3b95767f3	LmntTTSService: add model param and additional languages	2025-05-16 04:24:57 +00:00
Mark Backman	90f27a3090	Merge pull request #1816 from pipecat-ai/mb/add-minimax-tts ... Add MiniMax TTS	2025-05-15 18:05:13 -04:00
Mark Backman	b6f09defc9	Add MiniMax TTS	2025-05-15 18:02:29 -04:00
Aleix Conchillo Flaqué	95c25efab7	remove SileroVAD() frame processor	2025-05-15 11:55:20 -07:00
Mark Backman	119fd5ba7d	Merge pull request #1025 from fatwang2/main ... added hailuo tts service	2025-05-15 14:29:24 -04:00
Mark Backman	7a5205dbda	Fix: Resolve an issue where tracing imports were required	2025-05-14 12:29:08 -04:00
Thu Nguyen	15a5028d23	Revert log changes	2025-05-14 22:28:25 +08:00
Thu Nguyen	fee2648ac0	Handle audio transcript from gpt-4o-audio and clean up logs	2025-05-14 13:02:22 +07:00
getchannel	e27da96cdc	Rename file_api to file_api.py ... added proper .py to file name.	2025-05-13 22:01:02 -04:00
Mark Backman	50f6235edb	Add support for OpenTelemetry tracing (#1729) ... * Also added TurnTrackingObserver, TurnTraceObserver, foundational 29, open-telemetry-example	2025-05-13 17:18:11 -04:00
Aleix Conchillo Flaqué	83a4c7d443	RTVIProcessor: remove unused code	2025-05-13 11:26:37 -07:00
Aleix Conchillo Flaqué	8171fec925	SmallWebRTCConnection: complain if av package not found	2025-05-13 11:26:37 -07:00
Aleix Conchillo Flaqué	175f352ea7	add FrameProcessor.setup() to setup processors before StartFrame	2025-05-13 11:26:35 -07:00
kompfner	9a621f0c54	Merge pull request #1805 from pipecat-ai/pk/aws-nova-sonic-aggregate-user-transcription-text ... AWS Nova Sonic service - aggregate user transcription text; it was fr…	2025-05-13 09:13:58 -04:00
Paul Kompfner	55fc24e933	AWS Nova Sonic service - aggregate user transcription text; it was fragmented across many conversation history messages before	2025-05-13 09:13:28 -04:00
Filipi da Silva Fuchter	b14608f09b	Merge pull request #1799 from pipecat-ai/daily_audio_source ... Using audio source for capturing Daily's participant audio	2025-05-13 08:15:10 -03:00
Aleix Conchillo Flaqué	f800e35ccb	tests: allow passing observers to run_test()	2025-05-12 17:53:02 -07:00
Aleix Conchillo Flaqué	b33a60f3a5	Merge pull request #1793 from pipecat-ai/khk/deepgram-async-fix ... Fix Deepgram TTS streaming	2025-05-12 09:59:46 -07:00
Filipi Fuchter	d22dbb1a6d	Fixing ruff format.	2025-05-12 10:36:21 -03:00
Filipi Fuchter	133d7ee33a	Fixing the default audio source for capture_participant_audio	2025-05-12 10:16:32 -03:00
nikp06	537bd1c58d	Update ai_services.py ... fix: correct deprecation warning format in ai_services module	2025-05-12 12:01:13 +02:00
Kwindla Hultman Kramer	5ef519fe2c	Fix Deepgram TTS to use stream_raw()	2025-05-11 15:40:31 -07:00
Angelo Giacco	b57dfb3b5d	fix lint	2025-05-10 16:36:26 +01:00
Angelo Giacco	0355ed4aa1	move api key to ws header	2025-05-10 16:34:01 +01:00
Angelo Giacco	1e76cc7bdc	fix: elevenlabs api key	2025-05-10 16:09:20 +01:00
Aleix Conchillo Flaqué	f31efa42c9	GoogleLLMService: deprecate google-generativeai	2025-05-09 09:14:43 -07:00
getchannel	d86502e79a	add file_api __init__.py	2025-05-09 10:53:31 -04:00
getchannel	59c7744590	add FileData class events.py	2025-05-09 10:52:04 -04:00
getchannel	949971dea9	Create file_api	2025-05-09 10:51:24 -04:00
getchannel	cd4a893c65	add FileAPI to gemini.py	2025-05-09 10:50:27 -04:00
Paul Kompfner	c83c5b5a34	Add missing Params export to AWS Nova Sonic module	2025-05-08 15:23:25 -04:00
Mark Backman	9e0b4fe5d1	Replace list with tuple	2025-05-07 17:21:09 -04:00
Mark Backman	75ce632f84	Add DebugLogObserver	2025-05-07 17:21:08 -04:00
Mark Backman	efeb96c4e8	Remove unused imports	2025-05-07 17:20:42 -04:00
kompfner	fb5438e9c2	Merge pull request #1770 from pipecat-ai/pk/amazon-nova-sonic-interruption-reliability ... AWS Nova Sonic service - make interruption handling more reliable, in…	2025-05-07 17:16:06 -04:00
Mark Backman	7da9f66e1c	Merge pull request #1761 from pipecat-ai/mb/elevenlabs-context-id ... Update ElevenLabsTTSService to use the new websocket API	2025-05-07 17:12:06 -04:00
Mark Backman	9e16e3d614	Update ElevenLabsTTSService to use the new websocket API	2025-05-07 17:09:52 -04:00
Paul Kompfner	84d040c6d0	AWS Nova Sonic service - make interruption handling more reliable, in terms of: ... - not getting the conversation into a "stuck" state - not losing assistant text that should've made it into the context	2025-05-07 16:34:18 -04:00
Mark Backman	f3e0beb8f1	Merge pull request #1762 from pipecat-ai/iss-1734-rtvi-function-call-breakage ... Revert breaking change in RTVI protocol for function calling	2025-05-07 15:25:22 -04:00
Aleix Conchillo Flaqué	ed00f7d071	add video_source field to UserImageRequestFrame	2025-05-07 11:50:21 -07:00