Aleix Conchillo Flaqué
|
a0d5ee3873
|
MinWordsUserTurnStartStrategy: single word interrupt if bot not speaking
|
2025-12-22 14:32:21 -08:00 |
|
Mark Backman
|
08a9b434c1
|
Merge pull request #3277 from pipecat-ai/mb/fix-deprecation-warning-LLMContextAssistantTimestampFrame
fix: Separate LLMContextAssistantTimestampFrame from OpenAILLMContext…
|
2025-12-22 13:51:26 -05:00 |
|
Mark Backman
|
2910b683a4
|
Fix STT services that rely on VAD stop speaking status to finalize the transcript (#3283)
Updates to AssemblyAISTTService, CartesiaSTTService, DeepgramSageMakerSTTService, DeepgramSTTService to use VADUser*SpeakingFrame
|
2025-12-22 12:54:06 -05:00 |
|
Mark Backman
|
00bb08bacc
|
fix: Update ElevenLabsRealtimeSTTService to use VADUser speaking frames
|
2025-12-21 15:57:42 -05:00 |
|
Mark Backman
|
65f23adf4a
|
fix: Separate LLMContextAssistantTimestampFrame from OpenAILLMContextAssistantTimestampFrame
|
2025-12-21 09:06:35 -05:00 |
|
Mrunmay Chichkhede
|
d7d979dde1
|
feat: Add GrokRealtimeLLMService for xAI Grok Voice Agent API (#3267)
|
2025-12-20 07:04:12 -05:00 |
|
Sam Sykes
|
76bae6e699
|
Update SpeechmaticsSTTService to use the python voice SDK
|
2025-12-19 19:59:18 -05:00 |
|
Aleix Conchillo Flaqué
|
5816f960cc
|
LLMUserAggregator: add on_user_turn_started/on_bot_turn_started events
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
9bf6668b52
|
LLMUserAggregator: show error if using turn analyzer in transport
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
4a32aa5266
|
TurnAnalyzerBotTurnStartStrategy: don't use text on interim transcriptions
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
c9048d3a0f
|
LLMUserAggregator: prevent consecutive user/bot turn starts
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
9e56d1ac65
|
TurnStartStrategies: set user and bot strategies defaults if None
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
83263a30af
|
llm_response: deprecate old LLMUserAggregatorParams and LLMAssistantAggregatorParams
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
169fc0b568
|
frames: deprecate emulated field in UserStartedSpeakingFrame/UserStoppedSpeakingFrame
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
a9cca0b934
|
LLMAssistantAggregatorParams: copy to llm_response_universal
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
dff6b5402a
|
LLMUserAggregator: use TranscriptionUserTurnStartStrategy for emulated interruptions
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
2cdf207227
|
turns: add TranscriptionUserTurnStartStrategy
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
a388ff927c
|
LLMUserAggregator: broadcast user started/stopped speaking frames
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
222ccbb471
|
SegmentedSTTService: use VAD user started/stopped speaking frames
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
49ebe34599
|
BaseInputTransport: broadcast SpeechControlParamsFrame
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
c4c4b4107b
|
TurnAnalyzerBotTurnStartStrategy: broadcast SpeechControlParamsFrame
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
7e6b0839b0
|
examples(foundational): don't use legacy LLMUserAggregatorParams
|
2025-12-19 14:47:02 -08:00 |
|
Aleix Conchillo Flaqué
|
d33c72a8b0
|
LLMUserAggregator: allow external user started/stopped speaking frames
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
962eb73cc4
|
frames: deprecated EmulateUserStartedSpeakingFrame/EmulateUserStoppedSpeakingFrame
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
76561da850
|
TranscriptionBotTurnStartStrategy: improve by using interim transcriptions
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
355fcf3282
|
BaseInputTransport: deprecate the use of turn analyzer in transport
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
359ac302f5
|
audio(interruptions): deprecate MinWordsInterruptionStrategy
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
223052e6e7
|
LLMUserAggregator: use new user and bot turn start strategies
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
0f6668d41b
|
PipelineTask: pass turn start strategies to StartFrame
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
6a62c8d6da
|
FrameProcessor: add user and bot turn start strategies
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
5dd3af25ac
|
frames: add turn start strategies to StartFrame
|
2025-12-19 14:47:01 -08:00 |
|
Aleix Conchillo Flaqué
|
76c79a7dfa
|
introduce new user and bot turn start strategies
|
2025-12-19 14:47:01 -08:00 |
|
Mark Backman
|
fac1a05eb5
|
Merge pull request #3268 from fixie-ai/mike/ttfb
Add ttfb tracking for Ultravox
|
2025-12-19 15:49:57 -05:00 |
|
kompfner
|
917c512aa8
|
Merge pull request #3263 from pipecat-ai/pk/deprecate-openai-llm-context
Deprecate `OpenAILLMContext` and associated things
|
2025-12-19 13:19:48 -05:00 |
|
Mike Depinet
|
5ec08ff1d8
|
Add ttfb tracking for Ultravox
|
2025-12-19 09:26:11 -08:00 |
|
Paul Kompfner
|
9b6f5853cf
|
Deprecate OpenAILLMContext and associated things
|
2025-12-19 11:23:06 -05:00 |
|
Mark Backman
|
5e94b20562
|
Merge pull request #3233 from jaydamani/jay/improve-elevenlabs-services
Improve Elevenlabs realtime transcription service
|
2025-12-18 19:07:43 -05:00 |
|
Aleix Conchillo Flaqué
|
274db3e05c
|
DailyTransport: add transport_source to transcription frames
|
2025-12-17 19:24:08 -08:00 |
|
Aleix Conchillo Flaqué
|
6c0e4be4ac
|
Merge pull request #3205 from gui217/feat/rnnoise
Feat/rnnoise
|
2025-12-17 18:22:22 -08:00 |
|
Aleix Conchillo Flaqué
|
159e403ae4
|
MoondreamService: yield vision response and text frames
|
2025-12-17 10:42:08 -08:00 |
|
Aleix Conchillo Flaqué
|
d3d50ac580
|
frames: added vision response and text frames
|
2025-12-17 10:42:08 -08:00 |
|
jay
|
83a3295a39
|
update error handling based on code review
|
2025-12-18 00:03:47 +05:30 |
|
Aleix Conchillo Flaqué
|
d07b37b288
|
scripts(evals): more eval prompts improvements
|
2025-12-17 09:55:12 -08:00 |
|
Mark Backman
|
ca97d9dc4b
|
Merge pull request #3249 from pipecat-ai/mb/cleanup-pipecat-version
Clean up use of pipecat version
|
2025-12-17 12:17:53 -05:00 |
|
Mark Backman
|
6d84f36d05
|
Merge pull request #3214 from pipecat-ai/mb/update-run-inference
Update run_inference to use the provided LLM configuration params
|
2025-12-17 12:03:50 -05:00 |
|
Paul Kompfner
|
cdd6f5aa6a
|
Fix Anthropic LLM's run_inference so that it works even when extended thinking is enabled
|
2025-12-17 11:55:46 -05:00 |
|
Mark Backman
|
f1a0d547ce
|
Clean up use of pipecat version
|
2025-12-17 11:49:54 -05:00 |
|
mattie ruth backman
|
b1b7fc6357
|
Bump the RTVI version to 1.1.0 and add pipecat versioning to the botReady about field
|
2025-12-17 11:48:02 -05:00 |
|
Mark Backman
|
16e304016d
|
SimpleTextAggregator: Strip whitespace in the returned aggregation
|
2025-12-17 11:33:39 -05:00 |
|
Mark Backman
|
21a55f6aae
|
Update run_inference to use the provided LLM configuration params
|
2025-12-17 10:58:05 -05:00 |
|