Paul Kompfner
836cf60611
Fix an issue where Grok Realtime would error out when running with SmallWebRTC transport.
...
The underlying issue was related to the fact that we were sending audio to Grok before we had configured the Grok session with our default input sample rate (16000), so Grok was interpreting those initial audio chunks as having its default sample rate (24000). We didn't see this issue when using the Daily transport simply because in our test environments Daily took a smidge longer than a reflexive (localhost) pure WebRTC connection, so we would only send audio to Grok *after* we had configured the Grok session with the desired sample rate.
2026-01-16 15:41:33 -05:00
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
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
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
Neil Ruaro
9942fcfeb2
updated per PR reviews
2026-01-16 01:20:17 +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
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
Aleix Conchillo Flaqué
9e705ce768
UserTurnController: reset user turn start strategies when turn triggered
2026-01-14 18:20:29 -08:00
Mark Backman
f3993f1775
fix to make on_user_turn_stop_timeout work with ExternalUserTurnStrategies
2026-01-14 20:10:56 -05:00
Ashot
5ae592f38e
Improve Async TTS interruption handling by using AudioContextTTSService class and add changelog fragments
2026-01-14 15:45:27 +04:00
aconchillo
4531d517da
Update changelog for version 0.0.99
2026-01-14 00:49:15 +00:00
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
Mark Backman
bb00d223c9
Update 26a to use context aggregator transcription events
2026-01-13 17:01:10 -05:00
Aleix Conchillo Flaqué
5612bf513b
LLMContext: fix create_audio_message
2026-01-13 13:53:34 -08:00
Mark Backman
5d90f4ea06
Merge pull request #3428 from pipecat-ai/mb/fix-tracing-none-values
...
Fix TTS, realtime LLM services could return unknown for model_name
2026-01-13 15:40:10 -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
66551ebdf5
Merge pull request #3426 from pipecat-ai/mb/changelog-3404
...
Add changelog fragments for PR 3404
2026-01-13 15:34:58 -05:00
Aleix Conchillo Flaqué
21534f7d83
added changelog file for #3430
2026-01-13 12:21:22 -08:00
Mark Backman
efbc0c8510
Fix TTS, realtime LLM services could return unknown for model_name
2026-01-13 12:12:15 -05:00
Himanshu Gunwant
d0f227189c
fix: openai llm model name is unknown ( #3422 )
2026-01-13 11:55:52 -05:00
Mark Backman
f00f9d9f1a
Add changelog fragments for PR 3404
2026-01-13 11:29:17 -05:00
Mark Backman
31daa889e8
Add append_trailing_space to TTSService to prevent vocalizing trailing punctuation; update DeepgramTTSService and RimeTTSService to use the arg
2026-01-13 10:38:54 -05:00
Mark Backman
2296caf529
Merge pull request #3414 from pipecat-ai/mb/changelog-3410
...
Update changelog for PR 3410.changed.md
2026-01-12 13:43:42 -05:00
Mark Backman
90ded6658d
Merge pull request #3403 from pipecat-ai/mb/inworld-tts-add-keepalive
...
InworldTTSService: Add keepalive task
2026-01-12 13:31:24 -05:00
Mark Backman
5743e2a99b
Update changelog for PR 3410.changed.md
2026-01-12 12:15:40 -05:00
Varun Pratap Singh
3e982f7a4a
refactor: rename audio_packet_bytes to fixed_audio_packet_size
2026-01-12 22:11:39 +05:30
Varun Pratap Singh
14a115f372
changelog: add fragments for PR #3410
2026-01-12 18:12:27 +05:30
Mark Backman
aac24ad2d4
InworldTTSService: Add keepalive task
2026-01-10 11:20:20 -05:00
Aleix Conchillo Flaqué
64609fe80f
BaseOutputTransport: ensure bot speaking flag is set on time
2026-01-09 20:40:25 -08:00
Aleix Conchillo Flaqué
b59c3eb470
GroqTTSService: switch to canopylabs/orpheus-v1-english
2026-01-09 18:14:48 -08:00
Aleix Conchillo Flaqué
d2696be03b
PipelineTask: add external pipeline task setup files
2026-01-09 16:42:27 -08:00
Aleix Conchillo Flaqué
a992f95c02
clarify changelog with #3343 fix
2026-01-09 10:37:16 -08:00
Aleix Conchillo Flaqué
edd8e07df6
update changelog with #3343 fix
2026-01-09 10:31:29 -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
dafcd0448f
added changelog for new assistant turn events
2026-01-09 09:50:21 -08:00
Aleix Conchillo Flaqué
5cbb21afb2
deprecate TranscriptProcessor and related dataclasses and frames
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
Aleix Conchillo Flaqué
fef79651ef
turns: add UserTurnProcessor for advanced pipeline user turn management
2026-01-09 09:21:28 -08:00
Aleix Conchillo Flaqué
199986815c
turns: add UserTurnController for user turn management
2026-01-09 09:21:28 -08:00
Filipi da Silva Fuchter
0a3c00f68b
Merge pull request #3391 from pipecat-ai/filipi/krisp_followup_improvements
...
Krisp VIVA follow-up improvements
2026-01-09 10:39:23 -05:00
marcus-daily
c4cc476c3d
Updating changelog
2026-01-09 15:07:13 +00:00
filipi87
8b7cc65ae6
Mentioning the Krisp Viva improvements in the changelog.
2026-01-09 10:43:01 -03:00
Mark Backman
4d61c5d7b2
Deprecate support for vad_events in DeepgramSTTService
2026-01-08 20:32:30 -05:00
Mark Backman
5d2fac9cd7
Add changelog fragment for PR 3366
2026-01-08 14:43:23 -05:00
Mark Backman
5e0e6822c7
Merge pull request #3360 from pipecat-ai/mb/openai-realtime-send-image
...
Add video input (e.g. image input) support for OpenAI Realtime
2026-01-08 13:26:35 -05:00
Mark Backman
2aadac7a4d
Update OpenAIRealtime image to video to align with GeminiLive
2026-01-08 13:23:08 -05:00
