Sam Sykes
adf5198423
Support for retry when 503 error to TTS API.
2025-11-11 13:49:14 +00:00
Mark Backman
ee494918a9
Prep for 0.0.94 hotfix
2025-11-10 16:50:58 -05:00
Mark Backman
8dd45af5b7
Deprecate KrispFilter
2025-11-10 16:35:11 -05:00
Paul Kompfner
913194844e
Make the mechanism of adding spaces when concatenating TTS (or speech-to-speech LLM) output text explicit and deterministic, rather than heuristic-based.
...
This fixes a bug where spaces were sometimes missing from assistant messages in context.
2025-11-10 14:22:32 -05:00
vipyne
c1c7a561ed
remove LivekitFrameSerializer
2025-11-10 11:06:12 -06:00
Mark Backman
2300941bb8
Revert "Merge pull request #3004 from pipecat-ai/mb/improve-concat-aggregated-text"
...
This reverts commit 5e7f59a0b02ad4122b77
2025-11-10 09:58:19 -05:00
Aleix Conchillo Flaqué
4cf9e1409e
update CHANGELOG for 0.0.93
2025-11-07 13:17:44 -08:00
Aleix Conchillo Flaqué
342a8b121b
pyproject: update simli to 0.1.25
2025-11-07 11:30:41 -08:00
Aleix Conchillo Flaqué
9b1192ca9b
Merge pull request #3001 from pipecat-ai/pk/openai-realtime-toolsschema-support
...
Added support for passing in a `ToolsSchema` in lieu of a list of pro…
2025-11-07 09:37:43 -08:00
Mark Backman
5e7f59a0b0
Merge pull request #3004 from pipecat-ai/mb/improve-concat-aggregated-text
...
Improve concatenate_aggregated_text string utility
2025-11-07 12:37:12 -05:00
Aleix Conchillo Flaqué
8d0364b630
restore vision/image backwards compatibility
2025-11-07 08:53:58 -08:00
Mark Backman
03001f8047
Update TranscriptProcessor unit tests
2025-11-07 11:44:04 -05:00
Paul Kompfner
c3306bb4f2
Support for passing in a ToolsSchema in lieu of a list of provider-specific dicts when updating OpenAIRealtimeLLMService using LLMUpdateSettingsFrame.
2025-11-07 10:18:29 -05:00
Paul Kompfner
925a6cc2ef
Added support for passing in a ToolsSchema in lieu of a list of provider-specific dicts when initializing OpenAIRealtimeLLMService.
...
I chose to go the somewhat hacky route of adding the `ToolsSchema` support into the `events.SessionProperties` model itself—even though we should never serialize that type when creating events—because the alternative seemed to be to create a new type for `OpenAIRealtimeLLMService` initialization parameters and then we'd have to contend with backward compatibility, which seemed like a bigger headache.
2025-11-07 09:50:26 -05:00
Aleix Conchillo Flaqué
4c8c44ecc3
BaseOutputTransport: send silence when EndFrame is received
2025-11-06 12:16:05 -08:00
Aleix Conchillo Flaqué
f6916428b1
FrameProcessor: add new broadcast_frame() method
2025-11-06 12:11:48 -08:00
Marcus
a14d00b806
Improved LocalSmartTurnAnalyzerV3 performance on systems with a low CPU count ( #2982 )
2025-11-06 14:42:05 -05:00
Mark Backman
1fb6d6bd23
GoogleSTTService: Add more robust handling of 409 errors
2025-11-06 14:35:53 -05:00
Mark Backman
94a3306679
Merge pull request #2995 from pipecat-ai/mb/fix-stt-mute-filter-stt-muting
...
fix: STTMuteFilter no longer sends STTMuteFrame
2025-11-06 14:35:07 -05:00
Mark Backman
58b552171d
Add pronunciation_dictionary_locators to ElevenLabs TTS Services
2025-11-06 14:13:51 -05:00
Mark Backman
4732a442d4
Merge pull request #2992 from pipecat-ai/mb/metrics-log-observer
...
Add MetricsLogObserver
2025-11-06 14:04:55 -05:00
Mark Backman
accdddce95
Add MetricsLogObserver
2025-11-06 14:01:20 -05:00
Mark Backman
f6b6aa8766
fix: STTMuteFilter no longer sends STTMuteFrame
2025-11-06 11:53:32 -05:00
Mark Backman
34d6f3fa00
fix: correct GoogleLLMService token counting
2025-11-06 10:01:37 -05:00
Mark Backman
c8c13ecee2
fix: DeepgramSTTService await is_connected()
2025-11-05 21:42:15 -05:00
Paul Kompfner
61aec08794
CHANGELOG item ordering tweak
2025-11-05 15:29:58 -05:00
Paul Kompfner
75245e1daa
Fix a bug in GeminiLiveLLMService where in some circumstances it wouldn't respond after a tool call
2025-11-05 15:29:04 -05:00
Paul Kompfner
24365aeefe
CHANGELOG wording fix
2025-11-05 15:29:04 -05:00
Paul Kompfner
29ef0f419f
Add typing formalizing MCPClient support for registering tools on an LLMSwitcher in addition to an LLMService.
2025-11-05 15:29:01 -05:00
Paul Kompfner
a9d78bd956
Make it possible to get a ToolsSchema out of an MCPClient without passing in an LLM service.
...
This allows folks to use `MCPClient` alongside the pattern of passing in tools at LLM init time, a pattern supported by speech-to-speech services such as `GeminiLiveLLMService`.
2025-11-05 15:28:23 -05:00
Paul Kompfner
e6f881bb08
Remove the "needs alternate schema" mechanism in MCPClient, moving the necessary schema massaging into GeminiLLMAdapter instead.
...
This does a couple of things:
- Makes the `MCPClient` LLM agnostic, setting us up for some upcoming improvements (like making it possible to use with `LLMSwitcher`)
- Makes `GeminiLLMAdapter` more robust, as the schema massaging that was previously only done in `MCPClient` is useful for all tools, not just for MCP-provided ones
2025-11-05 15:28:23 -05:00
Paul Kompfner
bee4165ba4
Add LLMSwitcher.register_direct_function()
2025-11-05 15:28:19 -05:00
Aleix Conchillo Flaqué
d844829538
Revert "fix interruption task frame context ordering"
2025-11-05 12:14:03 -08:00
Mark Backman
11b101e8a6
Merge pull request #2974 from pipecat-ai/mb/language-mapping-improvements
...
Improve language checking in STT and TTS services
2025-11-05 14:59:41 -05:00
Mark Backman
9a96e4060c
Bumped the fastapi dependency to <0.122.0
2025-11-05 13:13:47 -05:00
Aleix Conchillo Flaqué
234aae3091
FrameProcessor: use finished_event for push_interruption_task_frame_and_wait
2025-11-05 09:38:17 -08:00
Aleix Conchillo Flaqué
c33b81bb92
PipelineTask: set finished_event InterruptionFrame is received
2025-11-05 09:37:55 -08:00
Mark Backman
2ee54c985f
Improve language checking in STT and TTS services
2025-11-05 12:26:52 -05:00
Thu Nguyen
76c336644a
Merge branch 'main' into feature/whisper-stt-probability-metrics
2025-11-06 00:24:34 +07:00
Thu Nguyen
dd8711dee1
Added changelog
2025-11-06 00:23:42 +07:00
Mark Backman
c18ff999a5
Update GoogleVertexLLMService default model to gemini-2.5-flash
2025-11-05 11:28:41 -05:00
Mark Backman
80d127aaa4
Refactor GoogleVertexLLMService to use GoogleLLMService as a base class
2025-11-05 09:33:02 -05:00
Mark Backman
01f3421052
Fix: support request data in SmallWebRTC
2025-11-04 17:14:29 -05:00
Aleix Conchillo Flaqué
38f27ad991
PipelineTask: load observers from PIPECAT_OBSERVER_FILES
2025-11-04 12:10:53 -08:00
Mark Backman
0c38585034
Merge pull request #2973 from pipecat-ai/mb/cartesia-sonic-3-languages
...
Add sonic-3 languages to Cartesia TTS services
2025-11-04 14:43:06 -05:00
Paul Kompfner
a82158045a
Fix Gemini Live session resumption. The problem was that we weren't properly ignoring send errors during reconnection.
2025-11-04 09:18:40 -05:00
Mark Backman
b1533ddfc4
Add sonic-3 languages to Cartesia TTS services
2025-11-04 07:57:04 -05:00
Paul Kompfner
87131850bc
GeminiLiveLLMService supports context-provided system instruction and tools
2025-11-03 10:30:46 -05:00
Aleix Conchillo Flaqué
62e45f466a
EndFrame: add reason field to indicate why pipeline is being ended
2025-11-02 00:45:27 -07:00
Aleix Conchillo Flaqué
e85e93b9b1
CancelFrame: add reason field to indicate why pipeline is being cancelled
2025-11-02 00:44:47 -07:00
