Aleix Conchillo Flaqué
31f7082d12
DeepgramTTSService: use Deepgram's asyncrest instead of asyncio.to_thread
2025-04-16 14:40:59 -07:00
Aleix Conchillo Flaqué
6cea71270e
tts: use smaller audio chunk sizes
2025-04-16 14:40:59 -07:00
Aleix Conchillo Flaqué
d05b2d0e8d
TavusVideoService: fix rate limiting and max size
2025-04-16 14:40:59 -07:00
Mark Backman
ad40a0f076
Update OpenAILLMService and OpenPipeLLMService to use gpt-4.1 by default
2025-04-15 15:11:05 -04:00
chadbailey59
efae26a5a8
Client connect/disconnect events for DailyTransport ( #1544 )
...
* added multi transport example
* added working example
* restructured example and added readme
* removed image
* cleanup
* changed data type of callback signature
* removed pipecat example
* added changelog
2025-04-14 15:56:41 -05:00
Aleix Conchillo Flaqué
ab6be11a0e
SoundfileMixer: add mixing argument and require keywords
2025-04-14 08:30:56 -07:00
Filipi Fuchter
e1108466f6
Fixed an issue in SmallWebRTCTransport where an error was thrown if the client did not create a video transceiver.
2025-04-14 10:36:25 -03:00
Mark Backman
f6accbd510
Updating foundation examples to use SmallWebRTCTransport and pipecat-ai-small-webrtc-prebuilt ( #1534 )
...
Co-authored-by: Filipi Fuchter <filipi@daily.co >
2025-04-11 19:44:16 -04:00
Mark Backman
b9a2ed5b58
Fix: GeminiMultimodalLiveLLMService, add spaces between words in assistant context messages
2025-04-11 15:14:52 -04:00
Mark Backman
7ac12ffc85
Merge pull request #1550 from pipecat-ai/mb/cartesia-spelling-timestamps
...
Fix: Cartesia's spelling feature adds whole word to context
2025-04-11 15:13:55 -04:00
Filipi da Silva Fuchter
f623cf96f7
Merge pull request #1560 from pipecat-ai/bot_left_signalling
...
Bot left signalling message
2025-04-11 16:08:01 -03:00
Mark Backman
06be20eb16
Fix: Cartesia's spelling feature adds whole word to context
2025-04-11 15:04:58 -04:00
Filipi Fuchter
816b3a9545
Fixing ruff format
2025-04-11 15:37:16 -03:00
Filipi Fuchter
255666925b
Sending a new signalling message peerLeft.
2025-04-11 15:35:50 -03:00
Mark Backman
e28c199dd1
Add GeminiMultimodalLiveLLMService support for VAD Params
2025-04-11 11:46:48 -04:00
Mark Backman
121e6d2157
Add media resolution support to GeminiMultimodalLiveLLMService
2025-04-11 10:18:29 -04:00
Mark Backman
dbd7869de7
Add model transcription support
2025-04-11 10:02:52 -04:00
Mark Backman
b7d56d5ff0
Add language support for Gemini Live
2025-04-11 09:21:14 -04:00
Filipi Fuchter
6378a8ccd3
Starting to implement a signalling message to when the bot has left
2025-04-10 23:02:27 -03:00
Filipi da Silva Fuchter
b89f2611f7
Merge pull request #1539 from pipecat-ai/small_wbertc_mute_state
...
SmallWebRTC mute state
2025-04-10 11:26:53 -03:00
Filipi Fuchter
f71c09a4fd
Added support in SmallWebRTCTransport to detect when remote tracks are muted.
2025-04-10 11:22:37 -03:00
Mark Backman
3b9a8946f9
Update GeminiMultimodalLiveLLMService base_url
2025-04-10 08:17:52 -04:00
Mark Backman
db3620c4be
Merge pull request #1553 from balaji-atoa/main
...
feat: change default model name on live api
2025-04-10 08:10:35 -04:00
balaji-atoa
c79c1f65fc
feat: change default model name on live api
2025-04-10 11:59:11 +05:30
Mark Backman
8ad2ad0e59
Add image capture to SmallWebRTCTransport
2025-04-09 23:01:06 -04:00
Kwindla Hultman Kramer
1828127f41
small fix to wss base_url
2025-04-08 20:22:26 -07:00
Mark Backman
03b3635b0a
Merge pull request #1521 from pipecat-ai/mb/increase-bot-vad-stop-secs
...
Increase BOT_VAD_STOP_SECS for services with slower speech patterns
2025-04-07 14:44:31 -04:00
Mark Backman
aaa7b5e626
Merge pull request #1524 from pipecat-ai/mb/tts-generate-with-text
...
TTS: Skip generation when there is no text
2025-04-07 14:44:18 -04:00
Mark Backman
b03563765f
Fix: Set language for Azure TTS services
2025-04-07 09:24:31 -04:00
Filipi Fuchter
b42dc83696
Improvements for the SmallWebRTCTransport:
...
- Wait until the pipeline is ready before triggering the `connected` event.
- Queue messages if the data channel is not ready.
- Update the aiortc dependency to fix an issue where the 'video/rtx' MIME type
was incorrectly handled as a codec retransmission.
- Avoid initial video delays.
2025-04-04 16:33:57 -03:00
Filipi Fuchter
c4c92585f9
Fixed SmallWebRTCTransport to support dynamic chunk values.
2025-04-04 15:38:12 -03:00
Mark Backman
63146d6f85
TTS: Skip generation when there is no text
2025-04-03 16:15:58 -04:00
Mark Backman
a21be058e2
Increase BOT_VAD_STOP_SECS for services with slower speech patterns
2025-04-03 15:25:48 -04:00
Mark Backman
c226c20e12
Merge pull request #1519 from pipecat-ai/mb/ref-docs-toc
...
Docs: Update ToC With Adapters and Observers
2025-04-03 15:19:35 -04:00
Aleix Conchillo Flaqué
79f29e14dd
processors: add ProducerProcessor and ConsumerProcessor
2025-04-03 09:44:56 -07:00
Mark Backman
3536cbcd13
Add docstrings to FunctionSchema, update CONTRIBUTING.md with docstrings guidance, ignore __init__ docstrings if a class is sufficiently documented
2025-04-03 09:21:26 -04:00
Mark Backman
19a82f9522
Add verse voice and bump the OpenAI version
2025-04-03 08:23:59 -04:00
Aleix Conchillo Flaqué
909520f76e
Merge pull request #1508 from pipecat-ai/mb/gemini-push-stop-speaking-frame
...
LLMAssistantContextAggregator should push BotStoppedSpeakingFrames
2025-04-02 16:25:08 -07:00
Mark Backman
55a6e5aa4c
Add new voices to OpenAITTSService
2025-04-02 12:09:36 -04:00
Mark Backman
b85bd91d08
LLMAssistantContextAggregator should push BotStoppedSpeakingFrames
2025-04-01 23:35:09 -04:00
Aleix Conchillo Flaqué
5df5f6ae4c
transports(websocket): close connection from last transport
2025-04-01 18:32:03 -07:00
Aleix Conchillo Flaqué
80584e9138
TransportParams: set audio_out_10ms_chunks to 4
2025-04-01 15:13:28 -07:00
Aleix Conchillo Flaqué
1fd01e715d
Merge pull request #1503 from pipecat-ai/aleix/function-call-result-system-frame
...
frames: make FunctionCallResultFrame a SystemFrame
2025-04-01 15:08:26 -07:00
Aleix Conchillo Flaqué
a7a1cd0cde
Merge pull request #1502 from pipecat-ai/aleix/test-user-idle-py310
...
tests: fix test_user_idle_processor for python 3.10
2025-04-01 15:08:10 -07:00
Aleix Conchillo Flaqué
169b50af61
frames: make FunctionCallResultFrame a SystemFrame
2025-04-01 14:42:22 -07:00
Aleix Conchillo Flaqué
31311d8ac5
tests: fix test_user_idle_processor for python 3.10
2025-04-01 13:54:59 -07:00
Aleix Conchillo Flaqué
bfd06b321d
BaseOutputTransport: optimize BotSpeakingFrames
2025-04-01 11:11:49 -07:00
Aleix Conchillo Flaqué
b40ca391f5
BaseOutputTransport: allow setting 10ms output audio chunks
2025-04-01 10:48:36 -07:00
Aleix Conchillo Flaqué
43008c8c5b
Merge pull request #1501 from pipecat-ai/aleix/transcription-processor-interruption
...
TranscriptProcessor: send TranscriptionUpdateFrame after interruption
2025-04-01 10:46:16 -07:00
Aleix Conchillo Flaqué
3a37b11e56
TranscriptProcessor: send TranscriptionUpdateFrame after interruption
2025-04-01 10:21:21 -07:00
