Commit Graph

1962 Commits

Author SHA1 Message Date
Mark Backman
4a363bebf0 Add a set_language convenience method for GoogleSTTService 2025-03-12 07:58:29 -04:00
Mark Backman
5f97f6ff94 Add flush_audio() to LmntTTSService 2025-03-11 21:57:54 -04:00
Mark Backman
e6f269a903 Add flush_audio to FishTTSService 2025-03-11 21:48:41 -04:00
Lucas Rothman
ecc4411128 Tavus support for custom output rate 2025-03-11 16:02:33 -07:00
Aleix Conchillo Flaqué
740ba4e759 ai_services: fix abstractmethod issues 2025-03-11 14:29:03 -07:00
Filipi Fuchter
c6c0b73345 P2P WebRTC transport option to Pipecat: SmallWebRTCTransport. 2025-03-11 11:35:39 -03:00
Filipi Fuchter
fde90ee01d Creating an EventEmitter util class 2025-03-11 11:33:47 -03:00
Filipi Fuchter
689a844aaf Created a new transport param to inform if the camera input should be enabled. 2025-03-11 11:33:24 -03:00
Filipi Fuchter
aab98b61a0 Fixed issue where sending too many images per second caused Gemini to ignore them. 2025-03-11 11:32:38 -03:00
Mark Backman
a62741df94 Add support for Chirp voices in GoogleTTSService 2025-03-11 07:56:27 -04:00
Kunal Shah
e1c8a09b60 [Cartesia] Update the default alias for Cartesia TTS Service 2025-03-10 14:43:58 -07:00
Filipi da Silva Fuchter
154fe65011 Merge pull request #1336 from pipecat-ai/fixing_function_calling_examples
Pipecat small fixes and refactored function calling examples
2025-03-07 16:10:27 -03:00
Aleix Conchillo Flaqué
06c742a2ad AudioBufferProcessor: add on_user_turn_audio_data and on_bot_turn_audio_data 2025-03-06 11:49:01 -08:00
Filipi Fuchter
55b0797fd5 Removing the extra examples inside the unified-format-function-calling folder 2025-03-06 12:00:22 -03:00
Filipi Fuchter
2d114b15f9 Adding missing flush_audio method to AzureTTSService. 2025-03-06 10:34:25 -03:00
Filipi Fuchter
26000b616d Fixing the base_whisper services to implement set_language. 2025-03-06 10:15:04 -03:00
Aleix Conchillo Flaqué
bb29e50adb introduce BaseObject class 2025-03-05 13:38:53 -08:00
Filipi Fuchter
a840b0e815 Prevents pytest from collecting TestFrameProcessor. 2025-03-05 14:11:52 -03:00
Filipi Fuchter
5967ac0d4f Implementing unified format for function calling. 2025-03-05 14:10:32 -03:00
Michael Louis
3fe7c1d730 Added ultravox service 2025-03-04 13:59:03 -05:00
kompfner
9f3c0219d7 Merge pull request #1329 from pipecat-ai/add-permissions-to-daily-meeting-token-properties
Add the `permissions` property to `DailyMeetingTokenProperties`
2025-03-03 14:44:10 -05:00
Aleix Conchillo Flaqué
ec36fef26e updated CHANGELOG and fix GladiaSTTService formatting 2025-03-03 09:53:03 -08:00
allenmylath
5f1848d24b Update gladia.py (#1317)
* Update gladia.py

According to gladia docs 
https://docs.gladia.io/api-reference/v2/live/init
speech threshould value close to 1 enables gladia to better isolate speeech from noise.
2025-03-03 09:51:11 -08:00
Aleix Conchillo Flaqué
17a1f30572 LLMService: add user/assistant args to create_context_aggregator() 2025-03-03 09:46:37 -08:00
Paul Kompfner
8e0dc1f256 Add the permissions property to DailyMeetingTokenProperties 2025-03-03 10:13:25 -05:00
Mark Backman
b8bc3d2565 Merge pull request #1326 from pipecat-ai/mb/11labs-speed
Add speed as InputParam to ElevenLabs TTS services
2025-03-02 15:20:01 -05:00
Mark Backman
ad7f1eec12 Create a function to build voice_settings dictionary 2025-03-02 08:27:29 -05:00
Mark Backman
29310b4e92 Add speed as InputParam to ElevenLabs TTS services 2025-03-02 08:19:44 -05:00
Kwindla Hultman Kramer
2f4d36a146 docstring fixup 2025-03-01 15:44:10 -08:00
Kwindla Hultman Kramer
6c9bb782b1 add __init__.py 2025-03-01 15:42:20 -08:00
Kwindla Hultman Kramer
010d9103d4 support for Azure OpenAI Realtime API 2025-03-01 15:39:19 -08:00
Aleix Conchillo Flaqué
8db9d16174 add new LLMFullResponseAggregator 2025-02-28 13:05:21 -08:00
Aleix Conchillo Flaqué
1c92fab1fb Merge pull request #1308 from Vaibhav159/vl_google_openai_format
adding GoogleLLMOpenAIBetaService
2025-02-28 12:04:37 -08:00
Vaibhav159
974717d1b9 sync with main 2025-03-01 01:16:21 +05:30
Vaibhav159
59fb631390 fixing function calling and adding example 2025-03-01 01:14:37 +05:30
Vaibhav159
4824220260 adding GoogleLLMOpenAIBetaService 2025-03-01 01:14:26 +05:30
Mark Backman
6018fc068c Rename ServerMessageFrame to RTVIServerMessageFrame and move to rtvi.py 2025-02-27 20:07:07 -05:00
Aleix Conchillo Flaqué
d5b634301f Merge pull request #1302 from pipecat-ai/aleix/cleanup-llm-tts-logging
services: minor LLM and TTS logging improvements
2025-02-27 13:51:04 -08:00
Adrian Cowham
803ea9d8bc update the canonical client so that the audio recording is optional as long as there is a transcript 2025-02-27 12:31:02 -08:00
Mark Backman
53d403af4b Remove the RTVIServerMessage logic from the RTVIProcessor 2025-02-27 12:50:43 -05:00
Mark Backman
26c68ccd7c Add a new generic server to client message and frame type 2025-02-26 18:59:06 -05:00
Aleix Conchillo Flaqué
fa010c8644 services: minor LLM and TTS logging improvements 2025-02-26 15:36:25 -08:00
Mark Backman
a5f41e22f7 Merge pull request #1299 from pipecat-ai/mb/add-track-level-recording
Added on_track_audio_data callback to AudioBufferProcessor for track level recording
2025-02-26 13:49:36 -05:00
Mark Backman
1ca2101e3a Added on_track_audio_data callback to AudioBufferProcessor for track level recording 2025-02-26 10:48:56 -05:00
Aleix Conchillo Flaqué
e80311c323 Merge pull request #1296 from pipecat-ai/aleix/google-always-send-text-with-audio
GoogleLLMService: always send text with audio
2025-02-26 07:47:56 -08:00
Aleix Conchillo Flaqué
2f24c422b6 Merge pull request #1289 from pipecat-ai/aleix/tts-http-improvements
small TTS http improvements
2025-02-26 07:47:26 -08:00
Mark Backman
1753cc99f4 PlayHTHttpTTSService now takes a separate protocol input 2025-02-26 08:01:54 -05:00
Aleix Conchillo Flaqué
bb89a036e5 google: always send text part when sending inline audio 2025-02-25 22:27:38 -08:00
Aleix Conchillo Flaqué
27161f8e3b BaseOutputTransport: cleanup audio buffer after bot stops talking 2025-02-25 21:39:47 -08:00
Aleix Conchillo Flaqué
8acf9a488b tts: some small HTTP-based services improvements 2025-02-25 21:39:47 -08:00