Aleix Conchillo Flaqué
aeadb40c3f
CartesiaTTSService: use AudioContextWordTTSService
...
By supporting multiple audio requests we fix an issue that was causing audio
overlapping.
2025-02-14 11:55:54 -08:00
Aleix Conchillo Flaqué
cacb07f4c2
introduce AudioContextWordTTSService
2025-02-14 11:55:54 -08:00
Aleix Conchillo Flaqué
af66a43056
Merge pull request #1222 from pipecat-ai/aleix/websocket-service-handle-clean-disconnection
...
WebsocketService: handle clean server disconnection
2025-02-14 10:33:54 -08:00
Aleix Conchillo Flaqué
e006dcf172
WebsocketService: handle clean server disconnection
...
The websocket async iterator doesn't raise an exception when the server
disconnects cleanly. We should handle that and raise an exception so we can
reconnect.
2025-02-14 10:11:56 -08:00
Filipi da Silva Fuchter
8588f8b0d8
Merge pull request #1220 from pipecat-ai/instant_voice_demo_example
...
Instant voice example.
2025-02-14 14:24:13 -03:00
Filipi Fuchter
bff54547b0
Instant voice example.
2025-02-14 14:19:17 -03:00
Mark Backman
b2754bf208
Merge pull request #1219 from pipecat-ai/mb/markdown-text-filter-tests
...
Add MarkdownTextFilter tests
2025-02-13 21:10:52 -05:00
Mark Backman
9a4942b0d0
Merge pull request #1218 from pipecat-ai/mb/user-idle-tests
...
Add UserIdleProcessor tests
2025-02-13 18:53:22 -05:00
Mark Backman
ed6201910b
Add MarkdownTextFilter tests
2025-02-13 18:51:46 -05:00
Mark Backman
ac5ebc587e
Add tests for UserIdleProcessor
2025-02-13 18:47:29 -05:00
Aleix Conchillo Flaqué
dff4c54e57
Merge pull request #1209 from pipecat-ai/aleix/reimplement-llm-response-aggregators
...
reimplement LLM response aggregators
2025-02-13 15:30:40 -08:00
Aleix Conchillo Flaqué
c744409651
SegmentedSTTService: fix process_audio_frame() arguments
2025-02-13 15:25:22 -08:00
Aleix Conchillo Flaqué
7578fbeaef
update google requirements
2025-02-13 15:25:22 -08:00
Aleix Conchillo Flaqué
5909dff423
LLMContextResponseAggregator: add VAD emulation support
2025-02-13 15:25:22 -08:00
Aleix Conchillo Flaqué
a6502df72c
services: forgot to pass context instead of user aggregator
2025-02-13 13:50:33 -08:00
Aleix Conchillo Flaqué
e0d24d7fc0
update CHANGELOG
2025-02-13 13:21:32 -08:00
Aleix Conchillo Flaqué
99779046a8
services: use push_context_frame()
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
67cdc0063a
BaseTransportOutput: allow pushing frames upstream
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
b28f752afa
tests: add anthropic and google aggregator tests
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
463078e375
initialize assistant aggregators with context and push upstream instead
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
84510fd521
LLMUserContextAggregator: add space between transcriptions
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
9f6a1c093a
LLMUserContextAggregator: reset user speaking time after bot interruption
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
b602e78625
tests: add OpenAI context aggregator tests
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
7c815121ea
LLMContextResponseAggregator: add missing reset() implementation
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
16a107948b
services: missing kwargs in anthropic/openai user context aggregator
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
839aa7d935
llm_response: add some initial docstrings to LLM aggregators
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
4cbcfe2b0b
LLMUserContextAggregator: interrupt the bot if VAD happened a while back
2025-02-13 13:20:38 -08:00
Aleix Conchillo Flaqué
91a628d1ba
UserResponseAggregator: implement on top of LLMUserResponseAggregator
2025-02-13 13:20:37 -08:00
Aleix Conchillo Flaqué
50288eeaaa
tests: add LLM response aggregators tests
2025-02-13 13:20:37 -08:00
Aleix Conchillo Flaqué
e1f2bbceb3
reimplement LLM response aggregators
2025-02-13 13:20:37 -08:00
Aleix Conchillo Flaqué
8bdd7ed0ed
tests: implement langchain tests with run_test()
2025-02-13 13:20:37 -08:00
Aleix Conchillo Flaqué
1b7dfe8126
tests: add a new SleepFrame
...
The new SleepFrame allow us to control when system frames are pushed to the
pipeline.
2025-02-13 13:20:37 -08:00
Aleix Conchillo Flaqué
d1ee851a65
tests: rename some variables to make things clearer
2025-02-13 13:20:37 -08:00
Filipi da Silva Fuchter
0358673b46
Merge pull request #1215 from pipecat-ai/instant_voice_demo
...
Instant voice demo improvements - part 02
2025-02-13 18:14:15 -03:00
Filipi Fuchter
16fe1b10e9
- Added support for the RTVIProcessor to handle buffered audio in base64 format, converting it into InputAudioRawFrame for transport.
...
- Added support for the `RTVIProcessor` to trigger `start_audio_in_streaming` only after the `client-ready` message.
2025-02-13 18:08:55 -03:00
Filipi Fuchter
f001819df8
- Added a new audio_in_stream_on_start field to TransportParams.
...
- Added a new method `start_audio_in_streaming` in the `BaseInputTransport`.
- Updated `DailyTransport` to respect the `audio_in_stream_on_start` field, ensuring it only starts receiving the audio input if it is enabled.
2025-02-13 18:08:36 -03:00
Filipi Fuchter
dceec60186
Updated FastAPIWebsocketOutputTransport to send TransportMessageFrame and TransportMessageUrgentFrame to the serializer.
2025-02-13 18:07:33 -03:00
Filipi Fuchter
b96979a4ed
Update WebsocketServer to not wrap the message inside a text frame.
2025-02-13 18:07:04 -03:00
Mark Backman
745c40def4
Merge pull request #1214 from pipecat-ai/mb/stt-mute-tests
...
Improve STTMuteFilter, add tests
2025-02-13 09:50:43 -05:00
Mark Backman
42ab62716d
Merge pull request #1198 from pipecat-ai/mb/more-whisper-params
...
Add prompt and temperature args to OpenAI and Groq hosted Whisper STT…
2025-02-13 09:16:38 -05:00
Mark Backman
16ba2010aa
Refactor process_frame to be more consistent
2025-02-13 09:15:29 -05:00
Mark Backman
ec0ca46617
Fix temperature docstrings to reference optional
2025-02-13 09:04:20 -05:00
Mark Backman
6ff1f526ff
Merge pull request #1216 from pipecat-ai/mb/google-cloud-speech
...
Add the google-cloud-speech package to the google dependency
2025-02-13 07:04:34 -05:00
Mark Backman
84143cc80c
self._muted now returns from STT process_audio_frames
2025-02-13 07:00:44 -05:00
Mark Backman
229dccedc6
Add the google-cloud-speech package to the google dependency
2025-02-12 23:19:17 -05:00
Aleix Conchillo Flaqué
68aaa1f8f4
Merge pull request #1213 from pipecat-ai/aleix/base-transport-output-bot-vad-stop-secs
...
BaseOutputTransport: use specific VAD stop secs for the bot
2025-02-12 19:01:56 -08:00
Aleix Conchillo Flaqué
f110a45c85
BaseOutputTransport: use specific VAD stop secs for the bot
2025-02-12 19:01:39 -08:00
Mark Backman
1e8a86de63
Handle starting muted, add tests
2025-02-12 19:01:49 -05:00
Mark Backman
ee93e2a2b1
Reorder frame pushing for STTMuteFilter, update STTMuteFrame to SystemFrame
2025-02-12 15:51:18 -05:00
Mark Backman
2e87a019a8
Merge pull request #1208 from pipecat-ai/mb/stt-mute-first-bot-speech
...
Add new STTMuteStrategy: MUTE_UNTIL_FIRST_BOT_COMPLETE
2025-02-12 12:21:02 -05:00
