Mark Backman
40562402a2
Changelog entry for Cartesia model update
2025-03-10 21:10:11 -04:00
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
Aleix Conchillo Flaqué
bb29e50adb
introduce BaseObject class
2025-03-05 13:38:53 -08:00
Filipi Fuchter
76d36a312b
Adding the unified format function calling to the changelog.
2025-03-05 14:18:37 -03:00
Aleix Conchillo Flaqué
ec36fef26e
updated CHANGELOG and fix GladiaSTTService formatting
2025-03-03 09:53:03 -08:00
Aleix Conchillo Flaqué
17a1f30572
LLMService: add user/assistant args to create_context_aggregator()
2025-03-03 09:46:37 -08:00
Kwindla Hultman Kramer
b9100beee3
Merge pull request #1327 from pipecat-ai/azure-realtime-changelog
...
CHANGELOG.md entry for AzureRealtimeBetaLLMService
2025-03-02 20:30:40 -08:00
Kwindla Hultman Kramer
3213e85b7d
CHANGELOG.md entry for AzureRealtimeBetaLLMService
2025-03-02 12:16:50 -08:00
Mark Backman
29310b4e92
Add speed as InputParam to ElevenLabs TTS services
2025-03-02 08:19:44 -05:00
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
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
daa52ff8df
update CHANGELOG for 0.0.58
2025-02-26 11:29:04 -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
530bb5233d
example: Added a foundational example (34) for audio recording
2025-02-26 13:44:32 -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
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
6722aae598
PipelineTask: force constructor keyword arguments
2025-02-25 18:58:47 -08:00
Aleix Conchillo Flaqué
66564392a6
Merge pull request #1293 from pipecat-ai/aleix/log-pipecat-version
...
log pipecat version on application startup
2025-02-25 18:57:52 -08:00
Aleix Conchillo Flaqué
f8f0578c3d
log pipecat version on application startup
2025-02-25 18:55:45 -08:00
Aleix Conchillo Flaqué
9a50f33e36
AudioContextWordTTSService: wait for all requested audio
2025-02-25 15:35:47 -08:00
Aleix Conchillo Flaqué
4bd5e9c0a7
Merge pull request #1285 from pipecat-ai/aleix/handle-stop-task-gracefully
...
handle stop task gracefully
2025-02-25 11:25:38 -08:00
Mark Backman
92cc6d39f2
TTSService: Remove newlines before sending text to TTS service to generate
2025-02-25 13:37:25 -05:00
Mark Backman
36a729cbfe
Set grok-2 as default model for GrokLLMSService
2025-02-25 10:00:45 -05:00
Aleix Conchillo Flaqué
68789dfcf0
frames: add new StopFrame
2025-02-24 21:34:23 -08:00
Aleix Conchillo Flaqué
6028f0f23a
PipelineTask: pass observers in contructor parameter
2025-02-24 21:29:17 -08:00
Aleix Conchillo Flaqué
e9a0959e28
Merge pull request #1283 from pipecat-ai/aleix/check-dangling-tasks
...
PipelineTask: add check_dangling_tasks parameter
2025-02-24 21:26:32 -08:00
Aleix Conchillo Flaqué
07b9be5308
PipelineTask: add check_dangling_tasks parameter
2025-02-24 17:33:10 -08:00
Aleix Conchillo Flaqué
40c2452d6e
google: updgrade OpenAILLMContext to GoogleLLMContext
2025-02-24 15:35:18 -08:00
Aleix Conchillo Flaqué
2110b79507
services(llm): add on_completion_timeout event
2025-02-24 14:55:36 -08:00
Aleix Conchillo Flaqué
fc544fa61c
Merge pull request #1272 from pipecat-ai/aleix/tts-websocket-interruptions
...
services: fix some TTS websocket service interruption handling
2025-02-24 14:54:41 -08:00
Mark Backman
d6f29a0f4b
Update AnthropicLLMService to use claude-3-7-sonnet-20250219 by default
2025-02-24 14:32:00 -05:00
Aleix Conchillo Flaqué
5b637bd826
services: fix some TTS websocket service interruption handling
2025-02-24 08:37:22 -08:00
Aleix Conchillo Flaqué
b29ab8c608
observers: add LLMLogObserver and TranscriptionLogObserver
2025-02-21 15:15:16 -08:00
Aleix Conchillo Flaqué
12bce2e8c0
utils: add support for ellipses in match_endofsentence()
2025-02-21 15:05:50 -08:00
Aleix Conchillo Flaqué
41720b1a13
LLMUserContextAggregator: don't reset timer with interim transcription
...
It turns out that in some cases we only get interim transcriptions (e.g. someone
is speaking very very softly or someone is talking in the background). In those
cases we don't want to interrupt the bot because there's really nothing to
interrupt the bot for.
We originally thought we should interrupt the bot right at the time we got an
interim frame, but this is causing too many false positives. It's actually
better to simply wait for a real transcription before interrupting (in case VAD
didn't interrupt).
2025-02-21 09:05:56 -08:00
Aleix Conchillo Flaqué
3ef4245166
Merge pull request #1265 from pipecat-ai/aleix/transport-remove-audio-out-is-live
2025-02-21 06:51:09 -08:00
Filipi Fuchter
7c7b4c52af
Fixed an issue where EndTaskFrame was not triggering on_client_disconnected or closing the WebSocket in FastAPI.
2025-02-21 09:11:58 -03:00
Aleix Conchillo Flaqué
01f083b7fc
transports: remove TransportParams.audio_out_is_live
2025-02-20 23:33:06 -08:00
Vaibhav159
9c5fe5c85e
fixing deepgram mismatch
2025-02-21 09:32:40 +05:30
Aleix Conchillo Flaqué
d04c4b36f3
AssistantContextAggregator: append aggregation and tools in the same turn
2025-02-20 17:29:43 -08:00
Aleix Conchillo Flaqué
69e6f3fdb7
rime: pass aiohttp session to constructor
2025-02-20 07:36:24 -08:00
Aleix Conchillo Flaqué
6809254963
tts: fix metrics and TTSStoppedFrame frame in HTTP services
...
Fixes #1247
2025-02-20 07:36:21 -08:00
