Commit Graph

838 Commits

Author SHA1 Message Date
Aleix Conchillo Flaqué
667aa0c25a Merge pull request #542 from joachimchauvet/main
Update LiveKit audio transport for changes introduced in v0.0.42
2024-10-12 14:13:02 -07:00
Adrian Cowham
4330374ba4 passing kwargs and forcing keyword-only arguments 2024-10-11 12:01:51 -07:00
Adrian Cowham
79c8aa2c4a ruff formatting 2024-10-11 11:35:02 -07:00
Adrian Cowham
083d221dd2 PR feedback 2024-10-11 11:29:01 -07:00
Adrian Cowham
917e482876 Merge branch 'main' into recording 2024-10-11 10:36:04 -07:00
Adrian Cowham
522d931950 better interruption handling by moving the processors after the transport output 2024-10-11 10:33:12 -07:00
Mark Backman
cbecae40a9 Mark the Markdown processor a util, and allow it to take inputs 2024-10-10 16:43:48 -04:00
Mark Backman
5b8753c8b6 Add speak_code input param 2024-10-10 13:17:37 -04:00
Mark Backman
3c5f9457f1 More edge case improvements 2024-10-10 12:07:00 -04:00
Mark Backman
788aec665b Add a new processor which removes markdown and special chars from TTS text 2024-10-10 07:11:31 -04:00
Mark Backman
e21fb520f9 Make bot-tts-text messages urgent 2024-10-08 17:07:08 -04:00
Aleix Conchillo Flaqué
8cdb9ab1ad rtvi: internal transport message should be urgent 2024-10-07 08:04:14 -07:00
Mark Backman
5dbf26d283 Handle cases where text is either a list or a string 2024-10-07 07:21:32 -04:00
Mark Backman
8001bab9b0 Remove another instance of urgent=true 2024-10-07 06:58:32 -04:00
Aleix Conchillo Flaqué
12d0686adc rtvi: rename bot-audio to bot-tts-audio 2024-10-06 16:50:55 -07:00
Aleix Conchillo Flaqué
a28a5e954a add TransportMessageSystemFrame 2024-10-06 16:50:12 -07:00
Aleix Conchillo Flaqué
bb966a89d2 rtvi: add RTVIUserLLMTextProcessor 2024-10-06 01:05:58 -07:00
Aleix Conchillo Flaqué
4a74eb3321 use isinstance tuples 2024-10-06 00:45:27 -07:00
joachimchauvet
86143f79a1 use new InputAudioRawFrame and OutputAudioRawFrame 2024-10-05 14:17:27 +03:00
joachimchauvet
b373bc82b5 match behavior of Daily's on_first_participant_joined 2024-10-05 14:17:27 +03:00
Mark Backman
7796a272ce Improve language handling for TTS services 2024-10-03 23:09:27 -04:00
Adrian Cowham
678e87fd31 comment back in some code 2024-10-03 14:12:23 -07:00
Adrian Cowham
4d81a2ebfe nuked the code that marks user audio in favor for InputAudioRawFrame. also moving to stereo instead of mono with the human and bot on their own channel. 2024-10-03 14:10:03 -07:00
Adrian Cowham
2d82702e04 merge from main 2024-10-03 09:42:06 -07:00
Mark Backman
45c7d36b2e Deepgram: disconnect and reconnect on language change 2024-10-03 12:31:42 -04:00
Aleix Conchillo Flaqué
65eeb0f1f6 Merge pull request #540 from pipecat-ai/cb/interruption-fix
Fixed RTVI `tts:interrupt` action not interrupting
2024-10-02 13:46:52 -07:00
Aleix Conchillo Flaqué
598936bc53 services: apply service language code before using service 2024-10-02 13:30:01 -07:00
Chad Bailey
b1bf6f7733 fixed botinterruptionframe 2024-10-02 19:43:51 +00:00
Aleix Conchillo Flaqué
0a37caf4b4 openai: fix image json logging 2024-10-02 11:57:50 -07:00
Aleix Conchillo Flaqué
6db65f4335 cartesia: use model_name instead of model_id 2024-10-02 11:57:36 -07:00
Aleix Conchillo Flaqué
3648874301 gladia: fix languages 2024-10-02 11:57:25 -07:00
Aleix Conchillo Flaqué
8bcb5d7fd2 services: async generators should yield frames 2024-10-02 11:57:08 -07:00
Aleix Conchillo Flaqué
8c01a900cd google: allow using GOOGLE_APPLICATION_CREDENTIALS 2024-10-02 11:56:01 -07:00
Mark Backman
cd2e29f285 Fix nested strings issue 2024-10-02 12:26:30 -04:00
Mark Backman
3d642df2b0 Revert aligning voice_id name in TTS service constructor 2024-10-02 11:07:48 -04:00
Mark Backman
d75a02dc51 Use Language enum and set languages accordingly 2024-10-01 21:03:01 -04:00
Mark Backman
28643b453d Update to use LLM, STT, TTS subclasses and remove setter methods 2024-10-01 20:30:27 -04:00
Mark Backman
88cca7bf68 Consolidate service UpdateSettingsFrame into a single ServiceUpdateSettingsFrame 2024-10-01 11:01:04 -04:00
Mark Backman
a397b859fe Add support for gender and google_style inputs to Google TTS 2024-10-01 10:39:45 -04:00
Kwindla Hultman Kramer
8aae4e9856 Merge pull request #531 from pipecat-ai/khk/function-calling-improvements 2024-10-01 07:23:38 -07:00
Kwindla Hultman Kramer
92d8b37229 implement vision for openai 2024-09-30 21:49:29 -07:00
Kwindla Hultman Kramer
0801fc578b Merge pull request #530 from pipecat-ai/khk/tts-say-fix
fix for multi-sentence tts say utterances
2024-09-30 20:59:53 -07:00
Kwindla Hultman Kramer
0d5cb84531 function calling testing and improvements 2024-09-30 20:59:28 -07:00
Kwindla Hultman Kramer
128355add5 fix for multi-sentence tts say utterances 2024-09-30 16:19:31 -07:00
Kwindla Hultman Kramer
0499fe41e4 get rid of some debug log lines used during development 2024-09-30 16:08:33 -07:00
Kwindla Hultman Kramer
6ad3437fd2 throw error if the llm tries to call a function that's not registered 2024-09-30 16:08:33 -07:00
Kwindla Hultman Kramer
a5c73ec829 handle openai multiple function calls 2024-09-30 16:08:30 -07:00
JeevanReddy
def04ac0ce openai can give multiple tool calls, current implementation assumes only one function call at a time. Fixed this to handle multiple function calls. 2024-09-30 16:07:56 -07:00
Kwindla Hultman Kramer
5d63615b1b Merge pull request #528 from pipecat-ai/khk/sentence-splits
TTS sentence aggregation fix
2024-09-30 16:07:21 -07:00
Kwindla Hultman Kramer
539e0b66fb small fix as per aleix 2024-09-30 16:05:32 -07:00