wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
7,074 Commits 276 Branches 111 Tags
dbeb6dd4abe4facd613c3a252f7f929d84442e48
Commit Graph

1034 Commits

Author SHA1 Message Date
James Hush
dbeb6dd4ab Refactor to use frame-based interruption control 
- Add EnableInterruptionsFrame custom frame for pipeline-based control
- Subclass VADUserTurnStartStrategy as DynamicVADUserTurnStartStrategy
- Use task.queue_frame() to toggle interruptions idiomatically
- Follows same pattern as MixerEnableFrame in 23-bot-background-sound.py
 2026-01-14 11:39:45 +08:00
James Hush
c2fdbc9e65 Add example demonstrating dynamic interruption toggling 
This example shows how to disable interruptions while still transcribing
user speech using the enable_interruptions parameter on user turn start
strategies (introduced in 0.0.99).

Key features demonstrated:
- VADUserTurnStartStrategy and TranscriptionUserTurnStartStrategy with
  enable_interruptions=False to prevent bot interruption
- Dynamic toggling via user_turn_controller.update_strategies() at runtime
- Transcription continues in both modes, only interruption behavior changes
 2026-01-14 11:23:29 +08:00
Mark Backman
b313395dc3 Fix 26a foundational 2026-01-13 19:31:24 -05:00
Aleix Conchillo Flaqué
bd9ee0d646 Merge pull request #3434 from pipecat-ai/aleix/context-appregator-pair-tuple 
context aggregator pair tuple
 2026-01-13 14:12:51 -08:00
Mark Backman
442e0e582d Merge pull request #3431 from pipecat-ai/mb/update-realtime-examples-transcript-handler 
Update GeminiLiveLLMService to push thought frames, update 26a for new transcript events
 2026-01-13 17:10:40 -05:00
Paul Kompfner
0ebdaba03c Remove dead import of TranscriptProcessor (which is now deprecated) 2026-01-13 17:02:57 -05:00
Aleix Conchillo Flaqué
ee82377d68 examples: fix 22d to push some CancelFrame and EndFrame 2026-01-13 14:01:53 -08:00
Aleix Conchillo Flaqué
861588e4a3 examples: update all examples to use the new LLMContextAggregatorPair tuple 2026-01-13 14:01:53 -08:00
Mark Backman
bb00d223c9 Update 26a to use context aggregator transcription events 2026-01-13 17:01:10 -05:00
Mark Backman
87d0dc9e24 Merge pull request #3412 from pipecat-ai/mb/remove-41a-b 
Remove foundational examples 41a and 41b
 2026-01-13 16:45:26 -05:00
kompfner
f6d09e1574 Merge pull request #3430 from pipecat-ai/pk/request-image-frame-fixes 
Fix request_image_frame and usage
 2026-01-13 15:36:44 -05:00
Mark Backman
b8e48dee7f Merge pull request #3433 from pipecat-ai/mb/port-realtime-examples-transcript-events 
Update examples to use transcription events from context aggregators
 2026-01-13 15:36:06 -05:00
Mark Backman
d591f9e108 Remove 28-transcription-processor.py 2026-01-13 15:20:59 -05:00
Mark Backman
aa2589d3be Update examples to use transcription events from context aggregators 2026-01-13 15:19:47 -05:00
Aleix Conchillo Flaqué
9d6067fa78 examples(foundational): speak "Let me check on that" in 14d examples 2026-01-13 12:11:30 -08:00
Aleix Conchillo Flaqué
027e54425a examples(foundational): associate image requests to function calls 2026-01-13 12:11:30 -08:00
Paul Kompfner
b937956dc8 Fix request_image_frame and usage 2026-01-13 13:23:01 -05:00
Mark Backman
41eef5efc4 Add 07j Gladia VAD foundational example, add to release evals 2026-01-13 11:36:15 -05:00
Mark Backman
89484e281d Remove foundational examples 41a and 41b 2026-01-12 10:11:58 -05:00
Aleix Conchillo Flaqué
65395b1112 examples(foundational): add missing transport.output() to 49c 2026-01-09 16:44:04 -08:00
Aleix Conchillo Flaqué
25f6ba76d6 add start timestamp to user and assistant turn messages 2026-01-09 09:50:21 -08:00
Aleix Conchillo Flaqué
8f47c569f9 examples(foundational): add 28-user-assistant-turns.py 2026-01-09 09:50:21 -08:00
Aleix Conchillo Flaqué
c16801e524 examples(foundational): update 49 series with on_assistant_thought 2026-01-09 09:50:21 -08:00
Aleix Conchillo Flaqué
9dff75cd44 examples: add 53-concurrent-llm-evaluation.py 2026-01-09 09:21:28 -08:00
filipi87
8b7cc65ae6 Mentioning the Krisp Viva improvements in the changelog. 2026-01-09 10:43:01 -03:00
filipi87
4d495ba74f Fixing ruff format. 2026-01-09 10:32:36 -03:00
filipi87
311da30802 Updating the Krisp Viva example to use Krisp turn model. 2026-01-09 10:19:13 -03:00
Mark Backman
2aadac7a4d Update OpenAIRealtime image to video to align with GeminiLive 2026-01-08 13:23:08 -05:00
Mark Backman
b90a34228f Update 19c to remove pausing audio and input 2026-01-08 13:00:45 -05:00
Mark Backman
8bf8ebd34b Remove start_audio_paused from OpenAI Realtime demos, and others 2026-01-08 13:00:45 -05:00
Mark Backman
3a7b489208 Add foundational 19c and add to evals 2026-01-08 13:00:45 -05:00
Aleix Conchillo Flaqué
2626154a64 update examples and tests copyright and use a proper dash in 2024-2026 2026-01-07 19:32:22 -08:00
filipi87
5412840a93 Added support for using the HeyGen LiveAvatar API with the HeyGenTransport. 2026-01-06 10:16:12 -03:00
Paul Kompfner
c53c49558f Fix the 20e example to use the proper conversation-start pattern for the Nova 2 Sonic model 2026-01-05 10:56:08 -05:00
Aleix Conchillo Flaqué
eb5a797b12 turns: rename bot turn start to user turn stop strategies 2025-12-30 14:33:58 -08:00
Aleix Conchillo Flaqué
97ab0d4f53 examples: added 52-live-translation without interruptions 2025-12-29 17:30:06 -08:00
Mark Backman
c28ed2206c DeepgramSTTService pushes user started/stopped speaking and interruption frames 2025-12-29 10:17:35 -08:00
Aleix Conchillo Flaqué
c821e9f8fd turns: add external user and bot turn start strategies 
External strategies are strategies where the logic for user turn start and turn
end come from a different processors (e.g. an STT).
 2025-12-29 10:17:35 -08:00
Aleix Conchillo Flaqué
0e8e3afc85 Merge pull request #3307 from pipecat-ai/aleix/simplify-turns-package-imports 
turns: simplify imports and don't require full strategy module path
 2025-12-28 18:51:23 -08:00
Aleix Conchillo Flaqué
5496aa722f turns: simplify imports and don't require full strategy module path 2025-12-28 16:20:15 -08:00
Aleix Conchillo Flaqué
5b93fb9609 PipelineTask: deprecate allow_interruptions parameter 2025-12-28 08:27:02 -08:00
Aleix Conchillo Flaqué
192ede6e34 Merge pull request #3298 from pipecat-ai/aleix/push-user-started-speaking-first 
push UserStartedSpeakingFrame before interruption
 2025-12-28 08:24:50 -08:00
Aleix Conchillo Flaqué
8b861d9143 LLMUserAggregator: move turn_start_strategies from PipelineTask 2025-12-28 08:16:34 -08:00
Aleix Conchillo Flaqué
094d9fd7d7 turns(mute): make strategies available in __init__ 2025-12-28 08:12:44 -08:00
Aleix Conchillo Flaqué
0efa36a04e examples(foundational): added 24-user-mute-strategy.py example 2025-12-27 13:49:31 -08:00
Aleix Conchillo Flaqué
260b7e7959 push UserStartedSpeakingFrame before interruption 2025-12-24 15:33:44 -08:00
Mark Backman
348fa5a719 Improve SessionProperties initialization: remove voice from args, set default for TurnDetection 2025-12-20 08:02:48 -05:00
Mark Backman
0576783c5e Improve sample_rate handling in GrokRealtimeLLMService 2025-12-20 07:46:31 -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