Commit Graph

7133 Commits

Author SHA1 Message Date
Aleix Conchillo Flaqué
c2a0735975 MinWordsUserTurnStartStrategy: don't aggregate transcriptions
If we aggregate transcriptions we will get incorrect interruptions. For example,
if we have a strategy with min_words=3 and we say "One" and pause, then "Two"
and pause and then "Three", this would trigger the start of the turn when it
shouldn't. We should only look at the incoming transcription text and don't
aggregate it with the previous.
2026-01-16 11:16:06 -08:00
Aleix Conchillo Flaqué
41cb53f6c2 Merge pull request #3479 from pipecat-ai/aleix/turns-mute-to-user-mute
turns: move mute to user_mute
2026-01-16 11:11:50 -08:00
Aleix Conchillo Flaqué
58552af8fd examples(foundational): remote STTMuteFilter example 2026-01-16 11:07:20 -08:00
Aleix Conchillo Flaqué
c7ab87b0cc turns: move mute to user_mute 2026-01-16 11:07:20 -08:00
kompfner
19fb3eed9f Merge pull request #3466 from pipecat-ai/pk/fix-aws-nova-sonic-rtvi-bot-output
Fix realtime (speech-to-speech) services' RTVI event compatibility
2026-01-16 09:56:13 -05:00
Mark Backman
b292b32374 Merge pull request #3461 from glennpow/glenn/websocket-headers
Allow WebsocketClientTransport to send custom headers
2026-01-15 20:26:36 -05:00
Glenn Powell
37914cb062 Removed import and added changelog entry. 2026-01-15 16:47:15 -08:00
Mark Backman
64a1ad2649 Merge pull request #3470 from pipecat-ai/mb/fix-docs-0.0.99
Docs fixes after 0.0.99
2026-01-15 17:34:44 -05:00
Mark Backman
4458ca1d24 Mock FastAPI 2026-01-15 17:29:47 -05:00
Mark Backman
21aaa48e62 Fix pydantic issues impacting autodoc 2026-01-15 17:29:47 -05:00
Mark Backman
e75c241030 Merge pull request #3468 from pipecat-ai/mb/camb-cleanuo
Clean up CambTTSService
2026-01-15 17:16:28 -05:00
Mark Backman
60216048a8 Docs fixes after 0.0.99 2026-01-15 16:40:42 -05:00
Mark Backman
f3c2e29fb4 Clean up CambTTSService 2026-01-15 15:59:17 -05:00
Paul Kompfner
ce99924be4 Add CHANGELOG entry describing fix for the missing "bot-llm-text" RTVI event when using realtime (speech-to-speech) services 2026-01-15 15:55:39 -05:00
Paul Kompfner
5de80a60d4 Fix "bot-llm-text" not firing when using Grok Realtime 2026-01-15 15:30:00 -05:00
Paul Kompfner
5753762350 Fix "bot-llm-text" not firing when using OpenAI Realtime 2026-01-15 15:16:08 -05:00
Paul Kompfner
885b318b04 Fix "bot-llm-text" not firing when using Gemini Live 2026-01-15 15:03:45 -05:00
Paul Kompfner
7a22d58cf4 Fix "bot-llm-text" not firing when using AWS Nova Sonic 2026-01-15 14:56:50 -05:00
Mark Backman
c8e4b462c9 Merge pull request #3460 from pipecat-ai/mb/reorder-07-examples
Renumber the 07 foundational examples
2026-01-15 14:44:21 -05:00
Mark Backman
30a3f42255 Merge pull request #3349 from eRuaro/feat/camb-tts-integration
Add Camb.ai TTS integration with MARS models
2026-01-15 14:43:12 -05:00
Neil Ruaro
26ddb2de2f minimal uv.lock update for camb-sdk 2026-01-16 03:18:01 +08:00
Neil Ruaro
f60eeaa212 reverted uv.lock, updated readthedocs.yaml, copyright year updates 2026-01-16 02:50:18 +08:00
Neil Ruaro
8cf72b36cb manually add camb-sdk to uv.lock, exclude camb from docs build 2026-01-16 02:26:38 +08:00
Neil Ruaro
38c3bcef96 exclude camb from docs build 2026-01-16 02:20:26 +08:00
Neil Ruaro
80604ba7b6 remove _update_settings method 2026-01-16 02:00:48 +08:00
Neil Ruaro
256c70c631 use UserTurnStrategies 2026-01-16 01:32:08 +08:00
Glenn Powell
0e3532c529 Allow WebsocketClientTransport to send custom headers 2026-01-15 09:31:48 -08:00
Neil Ruaro
9942fcfeb2 updated per PR reviews 2026-01-16 01:20:17 +08:00
Neil Ruaro
003c24ca6e Make model parameter explicit in docstring example 2026-01-16 01:18:37 +08:00
Neil Ruaro
ed120d014d Add model-specific sample rates, transport example, and fix audio buffer alignment 2026-01-16 01:18:37 +08:00
Neil Ruaro
e76a3d04f0 Update Camb TTS to 48kHz sample rate 2026-01-16 01:18:37 +08:00
Neil Ruaro
641d17007f Clean up Camb TTS service and tests 2026-01-16 01:18:37 +08:00
Neil Ruaro
9293b5f24a Migrate Camb TTS service from raw HTTP to official SDK
- Replace aiohttp with camb SDK (AsyncCambAI client)
- Add support for passing existing SDK client instance
- Simplify API: no longer requires aiohttp_session parameter
- Update example to use simplified initialization
- Rewrite tests to mock SDK client instead of HTTP servers
2026-01-16 01:18:37 +08:00
Neil Ruaro
c1f3cbd1d4 Yield TTSAudioRawFrame directly instead of calling private method 2026-01-16 01:18:37 +08:00
Neil Ruaro
78fa2ab65e Update default voice ID, fix MARS naming, and clean up example 2026-01-16 01:18:37 +08:00
Neil Ruaro
56da2caeed Update Camb.ai TTS inference options 2026-01-16 01:18:37 +08:00
Neil Ruaro
a541d65255 Update MARS model names to mars-flash, mars-pro, mars-instruct
Rename model identifiers from mars-8-* to the new naming convention:
- mars-8-flash -> mars-flash (default)
- mars-8 -> removed
- mars-8-instruct -> mars-instruct
- Added mars-pro
2026-01-16 01:18:37 +08:00
Neil Ruaro
a3d7e9eafe Address PR feedback: add --voice-id arg, remove test script
- Add --voice-id CLI argument to example (default: 2681)
- Remove test_camb_quick.py from examples/ (tests belong in tests/)
- Update docstring with new usage
2026-01-16 01:18:36 +08:00
Neil Ruaro
54933bea2a Rename changelog to PR number 2026-01-16 01:18:36 +08:00
Neil Ruaro
fcab9899cc Add changelog entry for Camb.ai TTS integration 2026-01-16 01:18:36 +08:00
Neil Ruaro
be098e85db Remove non-working Daily/WebRTC example
The Daily transport example had authentication issues. Keeping the
local audio example (07zb-interruptible-camb-local.py) which works.
2026-01-16 01:18:36 +08:00
Neil Ruaro
ed0ff46a87 added local test 2026-01-16 01:18:36 +08:00
Neil Ruaro
7ae0d651d6 added cambai tts integration 2026-01-16 01:18:36 +08:00
Mark Backman
efd4432cfb Renumber the 07 foundational examples 2026-01-15 10:26:17 -05:00
kompfner
24082b84f2 Merge pull request #3453 from pipecat-ai/pk/consistency-pass-on-user-started-stopped-speaking-frames
Do a consistency pass on how we're sending `UserStartedSpeakingFrame`…
2026-01-15 09:24:14 -05:00
Aleix Conchillo Flaqué
dcd5840341 Merge pull request #3455 from pipecat-ai/aleix/reset-user-turn-start-strategies
UserTurnController: reset user turn start strategies when turn triggered
2026-01-14 19:28:32 -08:00
Aleix Conchillo Flaqué
9e705ce768 UserTurnController: reset user turn start strategies when turn triggered 2026-01-14 18:20:29 -08:00
Mark Backman
965466cc09 Merge pull request #3454 from pipecat-ai/mb/external-turn-strategies-timeout
fix to make on_user_turn_stop_timeout work with ExternalUserTurnStrat…
2026-01-14 20:15:31 -05:00
Mark Backman
f3993f1775 fix to make on_user_turn_stop_timeout work with ExternalUserTurnStrategies 2026-01-14 20:10:56 -05:00
Paul Kompfner
e107902b14 Do a consistency pass on how we're sending UserStartedSpeakingFrames and UserStoppedSpeakingFrames. The codebase is now consistent in broadcasting both types of frames up and downstream. 2026-01-14 18:47:15 -05:00