Commit Graph

9290 Commits

Author SHA1 Message Date
Mark Backman
ddcc1fbb2f Add foundational example 35 2025-03-18 07:30:11 -04:00
Mark Backman
e731a0d41f Add PairPatternAggregator 2025-03-18 07:30:11 -04:00
Mark Backman
4918eab4e8 Merge pull request #1371 from pipecat-ai/mb/openai-realtime-transcription
Add TranscriptProcessor support for OpenAIRealtimeBetaLLMService
2025-03-18 07:28:07 -04:00
Mark Backman
11987765d8 Merge pull request #1381 from pipecat-ai/mb/recording-example-stt
Update the 34-audio-recording.py example to include an STT processor
2025-03-18 07:20:42 -04:00
Mark Backman
6f09ee25b8 Merge pull request #1385 from pipecat-ai/mb/add-neuphonic-readme
Add Google Imagen and Neuphonic TTS to README
2025-03-18 07:20:15 -04:00
Mark Backman
83dda8a759 Merge pull request #1390 from adnansiddiquei/add-neuphonic-languages
Added 5 new languages for Neuphonic: FR, PT, RU, ZH, HI.
2025-03-18 07:18:27 -04:00
Adnan Siddiquei
188677e601 Added 4 new languages: FR, PT, RU, ZH, HI. 2025-03-18 10:35:22 +00:00
balalo
dc5067407d Fix ruff check 2025-03-18 11:12:51 +01:00
balalo
1c19777d5e Fix format 2025-03-18 11:09:40 +01:00
balalo
2e1a18503b Set tool choice from context aggregator 2025-03-18 10:41:43 +01:00
Lucas Rothman
c57fa93a70 Renamed to sample_rate 2025-03-17 16:22:36 -07:00
Mark Backman
6885d07e88 Simplify the TranscriptProcessor _emit_aggregated_text logic 2025-03-17 16:36:03 -04:00
Mark Backman
acd0660f66 Update GeminiMultimodalLiveLLMService to work with the TranscriptProcessor 2025-03-17 16:36:03 -04:00
Mark Backman
3f002f8ffb Remove unnecessary TranscriptProcessor examples 2025-03-17 16:36:02 -04:00
Mark Backman
d5776c27f4 Update 19-openai-realtime-beta 2025-03-17 16:35:35 -04:00
Mark Backman
6e6905405b Update CHANGELOG 2025-03-17 16:35:35 -04:00
Mark Backman
571c10403f tests: Add additional coverage to test_transcript_processor 2025-03-17 16:35:35 -04:00
Mark Backman
5b6b700214 OpenAIRealtimeBetaLLMService outputs a TTSTextFrame 2025-03-17 16:35:35 -04:00
Mark Backman
1ad8e28025 Update TranscriptProcessor to more robustly handle different TTSTextFrame outputs 2025-03-17 16:35:35 -04:00
Mark Backman
3458f1b6de Add Google Imagen to README 2025-03-17 11:43:40 -04:00
Mark Backman
02dbef8f5a Add Neuphonic TTS to README 2025-03-17 11:28:51 -04:00
Zac
1baa52a17e Enhanced whisper.py with MLX Whisper model support and added optional mlx-whisper to pyproject.toml. Added error handling for missing modules and created a new WhisperSTTServiceMLX class for MLX Whisper integration. 2025-03-16 02:18:54 -04:00
Mark Backman
c1382b0691 Update the 34-audio-recording.py example to include an STT processor 2025-03-15 20:30:35 -04:00
Vaibhav159
5f000efc61 adding example 2025-03-15 10:36:26 +05:30
Vaibhav159
fa7da8f5f6 adding vertex llm 2025-03-15 10:21:40 +05:30
Mark Backman
8b86f6991d Merge pull request #1343 from pipecat-ai/mb/pipecat-cloud-example
Add a Pipecat Cloud deployment example
2025-03-14 20:49:45 -04:00
Mark Backman
d3cd1a6c59 Update with latest starter 2025-03-14 20:40:33 -04:00
Mark Backman
24220f38f0 Add a Pipecat Cloud deployment example 2025-03-14 20:40:29 -04:00
Aleix Conchillo Flaqué
1f8752ab03 Merge pull request #1378 from pipecat-ai/aleix/remove-deprecations
removed most deprecations
2025-03-14 14:42:34 -07:00
Aleix Conchillo Flaqué
16d7df1c9f removed most deprecations 2025-03-14 14:37:08 -07:00
Aleix Conchillo Flaqué
2474211291 Merge pull request #1379 from pipecat-ai/aleix/introduce-text-aggregators
introduce text aggregators
2025-03-14 13:03:49 -07:00
Aleix Conchillo Flaqué
b632d71465 TTSService: flush_audio() should be in the base class 2025-03-14 10:48:25 -07:00
Aleix Conchillo Flaqué
f8610a69a5 introduce text aggregators 2025-03-14 10:48:25 -07:00
Aleix Conchillo Flaqué
624a454f8b Merge pull request #1366 from adnansiddiquei/neuphonic-tts-plugin
Add integration for Neuphonic TTS
2025-03-14 10:27:24 -07:00
Aleix Conchillo Flaqué
11ba08b7ba Merge pull request #1377 from pipecat-ai/aleix/task-upstream-downstream-filters
PipelineTask: only call event handlers if a filter is matched
2025-03-14 08:49:24 -07:00
Adnan Siddiquei
11b13d053b Fixed a bug from previous commit. Removed the concept of model from Neuphonic. 2025-03-14 11:17:22 +00:00
Adnan Siddiquei
7dec8431e1 Review comments by aconchillo. 2025-03-14 10:52:13 +00:00
Aleix Conchillo Flaqué
ce3f3b2edb Merge pull request #1372 from pipecat-ai/khk-fix-multimodal-live-example
fix for 26-gemini-multimodal-live.py
2025-03-13 20:22:07 -07:00
Aleix Conchillo Flaqué
1b3b4ee04a PipelineTask: only call event handlers if a filter is matched 2025-03-13 18:44:30 -07:00
Mark Backman
676c5d9ba7 Merge pull request #1374 from pipecat-ai/mb/add-riva-to-readme 2025-03-13 20:41:05 -04:00
Mark Backman
6eb3a8409f README: Add Parakeet and FastPitch 2025-03-13 18:42:19 -04:00
Filipi Fuchter
526f9c2e06 Fixing the voice agent feedback when disconnected. 2025-03-13 18:41:40 -03:00
Kwindla Hultman Kramer
c9a31ea513 fix for 26-gemini-multimodal-live.py 2025-03-13 14:35:47 -07:00
Filipi Fuchter
2770d64a25 Fixing ruff format. 2025-03-13 17:38:11 -03:00
Filipi Fuchter
8a7e305619 Closing the old peer connection 2025-03-13 17:35:47 -03:00
Filipi Fuchter
8f2dadf5a0 Improving the reconnection logic to be able to recreate the peer connection in some cases. 2025-03-13 17:07:32 -03:00
Aleix Conchillo Flaqué
c0c7c5d600 Merge pull request #1370 from pipecat-ai/aleix/minor-ultravox-updates
services(ultravox): CHANGELOG, formatting and minor changes
2025-03-13 12:05:13 -07:00
Aleix Conchillo Flaqué
87004937be services(ultravox): CHANGELOG, formatting and minor changes 2025-03-13 11:49:18 -07:00
Aleix Conchillo Flaqué
b426be3067 Merge pull request #1331 from CerebriumAI/feature/ultravox
Added ultravox service
2025-03-13 10:40:00 -07:00
Aleix Conchillo Flaqué
b71e2b97ff Merge pull request #1368 from pipecat-ai/aleix/pipelinetask-frame-event-handlers
PipelineTask: add on_frame_reached_upstream and on_frame_reached_downstream
2025-03-13 10:31:33 -07:00