Paul Kompfner
bcf11ecbd4
Looks like the Deepgram Sagemaker TTS services aren't able yet to successfully disconnect/reconnect to apply runtime settings updates. For now, marking them as not yet supporting runtime settings updates.
2026-02-23 16:02:00 -05:00
Paul Kompfner
ff174dd1c2
Fix STT/TTS Deepgram Sagemaker 55-series examples (examples updating settings at runtime)
2026-02-23 16:02:00 -05:00
Paul Kompfner
e804060e17
Update COMMUNITY_INTEGRATIONS.md _update_settings examples
...
Simplify the reconnect example to show a common pattern (reconnect on any change) and improve the _warn_unhandled_updated_settings example to show selective handling of specific fields.
2026-02-23 15:45:00 -05:00
Paul Kompfner
30db5fea7c
Clarify that ServiceSettings and subclasses represent runtime-updatable settings
...
Update docstrings for ServiceSettings, LLMSettings, TTSSettings, and STTSettings to make clear these capture only the subset of service configuration that can be changed while the pipeline is running via UpdateSettingsFrame, not all constructor parameters.
2026-02-23 15:38:57 -05:00
Mark Backman
c527e1f30f
Add dataclass vs Pydantic BaseModel rule to CLAUDE.md
...
Document the existing convention: use @dataclass for frames and
internal pipeline data, use Pydantic BaseModel for configuration,
parameters, metrics, and external API data.
2026-02-23 14:26:16 -05:00
Paul Kompfner
029f3dbefb
Updating 55o ElevenLabsTTSService example to also exercise switching voices, which requires reconnect
2026-02-23 12:08:13 -05:00
kompfner
03cb0054f9
Merge branch 'main' into pk/service-settings-refactor
2026-02-23 11:46:03 -05:00
Mark Backman
6a7e9358c6
Merge pull request #3803 from pipecat-ai/mb/inline-smart-turn-v3-deps
...
Inline local-smart-turn-v3 deps for Poetry compatibility
2026-02-23 09:29:52 -05:00
Mark Backman
6a3718d33d
Inline local-smart-turn-v3 deps for Poetry compatibility
...
Replace self-referential `pipecat-ai[local-smart-turn-v3]` extra in core
dependencies with the actual packages (`transformers`, `onnxruntime`).
Self-referential extras are not supported by Poetry and cause dependency
resolution failures. Since these are required by the default turn stop
strategy (LocalSmartTurnAnalyzerV3), they belong in core dependencies.
- Remove `local-smart-turn-v3` optional extra from pyproject.toml
- Remove try/except ModuleNotFoundError guard (now always installed)
- Remove `--extra local-smart-turn-v3` from CI workflows
2026-02-23 09:00:36 -05:00
Om Chauhan
b390dc369c
added changelog
2026-02-21 18:33:29 +05:30
Om Chauhan
a18aa738e0
fix(realtime): handle response_cancel_not_active as non-fatal
2026-02-21 18:26:31 +05:30
Om Chauhan
9476b5d184
added changelog
2026-02-21 17:35:08 +05:30
Om Chauhan
f49658de15
skipping provider-specific messages during summarization
2026-02-21 17:19:50 +05:30
Aleix Conchillo Flaqué
b67af19d47
Merge pull request #3793 from pipecat-ai/changelog-0.0.103
...
Release 0.0.103 - Changelog Update
2026-02-20 16:42:46 -08:00
aconchillo
6d9c07b945
Update changelog for version 0.0.103
2026-02-20 16:39:36 -08:00
Aleix Conchillo Flaqué
18429f80f1
github(changelog): allow performance type
2026-02-20 16:32:40 -08:00
Aleix Conchillo Flaqué
0a54dc9721
Merge pull request #3792 from pipecat-ai/aleix/update-anthropic-default-model
...
Update default Anthropic model to claude-sonnet-4-6
2026-02-20 16:28:08 -08:00
Aleix Conchillo Flaqué
521f669051
Add changelog entries for PR #3792
2026-02-20 16:18:21 -08:00
Aleix Conchillo Flaqué
abb20f34ba
Update default Anthropic model to claude-sonnet-4-6
...
Update the default model in AnthropicLLMService and remove the
now-unnecessary explicit model from the function calling example.
2026-02-20 16:17:51 -08:00
Joshua Primas
d38b1d97d4
Added changelog
2026-02-20 16:13:44 -08:00
Joshua Primas
0b4568843b
Improved logging + error handling + pipecat bot name usage
2026-02-20 15:59:52 -08:00
Joshua Primas
35aba4128c
Adding the LemonSlice transport integration
2026-02-20 15:24:48 -08:00
Aleix Conchillo Flaqué
b1e72ad4b7
Merge pull request #3789 from pipecat-ai/aleix/fix-missing-await-and-interruption-hang
...
Fix missing await and interruption timeout hang
2026-02-20 14:59:11 -08:00
Aleix Conchillo Flaqué
f610fb95f9
Add changelog entries for PR #3789
2026-02-20 14:56:46 -08:00
Aleix Conchillo Flaqué
827032fefb
Unblock push_interruption_task_frame_and_wait after timeout
...
When the InterruptionFrame does not complete within the timeout the
caller was stuck in an infinite loop logging warnings. Now the event
is set after the first timeout so the processor can continue.
Also adds a keyword timeout parameter so callers can customize the
wait duration.
2026-02-20 14:56:42 -08:00
Aleix Conchillo Flaqué
af4ef95dc6
Fix missing await on add_audio_frames_message in Google audio examples
...
The method is async but was being called without await, silently
discarding the coroutine.
2026-02-20 14:24:22 -08:00
Aleix Conchillo Flaqué
0370bb15e4
update uv.lock
2026-02-20 13:47:04 -08:00
Aleix Conchillo Flaqué
2b3595485f
Merge pull request #3788 from dhruvladia-sarvam/v3-fix-final
...
initial
2026-02-20 13:46:18 -08:00
Paul Kompfner
af4226adbf
Add changelog entries for service settings refactor PR #3714
2026-02-20 15:26:17 -05:00
Paul Kompfner
29e2a861dc
Update AIService.set_model_name to AIService._sync_model_name_to_metrics to:
...
- indicate clearly that it's not meant for public use
- make it clear the `self._settings` is the single source of truth for model information
- set the stage for an upcoming change where `AIService` subclasses won't have to ever worry about explicitly calling an `AIService` method to sync model name to metrics
Across all services, switch from accessing `self._model_name` or `self.model_name` in favor of `self._settings.model`.
2026-02-20 15:02:50 -05:00
Filipi da Silva Fuchter
63c664becb
Merge pull request #3787 from pipecat-ai/filipi/refresh_active_audio_context
...
Fix race condition where context times out after sending second transcript
2026-02-20 14:50:38 -05:00
dhruvladia-sarvam
fecf462139
initial
2026-02-21 01:02:37 +05:30
Daksh Dua
023063759a
Changelog entry for TTS race condition fix.
2026-02-20 16:00:34 -03:00
Daksh Dua
c49eda98e7
Fix race condition where context times out after sending second transcript
2026-02-20 15:37:14 -03:00
Filipi da Silva Fuchter
5d07326e36
Merge pull request #3732 from pipecat-ai/filipi/tts_updates
...
Refactored audio context management in TTS services
2026-02-20 13:02:42 -05:00
filipi87
fa659311b6
Changelog entry
2026-02-20 14:57:59 -03:00
filipi87
125c423356
Refactored audio context management in TTS services to improve encapsulation and reduce code duplication
2026-02-20 14:57:44 -03:00
Filipi da Silva Fuchter
c9615c8db6
Merge pull request #3779 from pipecat-ai/filipi/filter_observer
...
Allowing to define the list of frame processors whose frames should be silently ignored by the RTVI observer.
2026-02-20 12:42:02 -05:00
Aleix Conchillo Flaqué
28c542f6ed
Merge pull request #3785 from pipecat-ai/mb/deepgram-sagemaker-tts
...
Add DeepgramSageMakerTTSService
2026-02-20 09:01:32 -08:00
Paul Kompfner
f5b86d9cdc
Actually, revert the change making it so that STTService takes model and language args at init time. It'll be up to the subclasses to append those to _settings (or better yet, provide their own service-specific _settings). This avoids rocking the boat too too much.
2026-02-20 11:26:28 -05:00
Aleix Conchillo Flaqué
5708c81b93
Merge pull request #3782 from pipecat-ai/aleix/fix-mutable-default-args-aggregator-pair
...
Fix mutable default arguments in LLMContextAggregatorPair
2026-02-20 08:02:18 -08:00
Paul Kompfner
f4e9825c03
Remove self._voice_id from TTS Service implementations in favor of self._settings.voice
2026-02-20 10:52:57 -05:00
Mark Backman
82ce3ea8de
Update 07c example to use DeepgramSageMakerTTSService
2026-02-20 08:10:41 -07:00
Mark Backman
62ada92188
Add changelog for PR #3785
2026-02-20 08:09:57 -07:00
Mark Backman
273692421f
Add DeepgramSageMakerTTSService for Deepgram TTS on AWS SageMaker
...
Adds a TTS service that connects to Deepgram models deployed on AWS
SageMaker endpoints via HTTP/2 bidirectional streaming. Supports the
Deepgram TTS protocol (Speak, Flush, Clear, Close) over the BiDi
client, with interruption handling and per-turn TTFB metrics.
Updates the example and env.example with separate STT/TTS endpoint names.
2026-02-20 08:08:00 -07:00
Paul Kompfner
5d8a5bf750
Add initialization of self._settings to service superclasses (STTService, TTSService, LLMService), using "generic" settings for those services (STTSettings, TTSSettings, LLMSettings)
2026-02-20 09:31:22 -05:00
Mark Backman
0a3e212f93
Merge pull request #3784 from pipecat-ai/mb/stt-sagemaker-finalize
...
Align DeepgramSageMakerSTTService finalize pattern with DeepgramSTTService
2026-02-20 09:26:23 -05:00
Mark Backman
43d686c622
Add changelog entry for PR #3784
2026-02-20 07:17:36 -07:00
Mark Backman
4d136e1e28
Align DeepgramSageMakerSTTService finalize pattern with DeepgramSTTService
2026-02-20 07:15:38 -07:00
Aleix Conchillo Flaqué
2024285c75
Add changelog entries for PR #3782
2026-02-19 20:52:31 -08:00
