wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
7,628 Commits 276 Branches 111 Tags
beb4e86b5f6dab95fe702cd6295bcd0f90aea291
Commit Graph

7628 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
filipi87
beb4e86b5f Fixing an issue in RTVI where we were sometimes receiving bot output messages before the bot started speaking. 2026-02-11 16:17:28 -03:00
Aleix Conchillo Flaqué
e75ccd9c2f Merge pull request #3717 from pipecat-ai/aleix/update-claude-md-pr-instructions 
Add /pr-submit skill and clean up CLAUDE.md
 2026-02-11 10:40:20 -08:00
Aleix Conchillo Flaqué
a80919ceff Move PR submission instructions from CLAUDE.md to /pr-submit skill 
Extract the procedural PR workflow into an actionable skill that can be
invoked with /pr-submit. CLAUDE.md is better suited for project context
and conventions, not step-by-step procedures.
 2026-02-11 09:57:42 -08:00
Aleix Conchillo Flaqué
1fe4538982 Update PR submission instructions in CLAUDE.md 
Expand the Pull Requests section with detailed step-by-step instructions
including branch naming, commit guidance, changelog generation, and PR
description updates.
 2026-02-11 09:51:10 -08:00
Filipi da Silva Fuchter
9a48d93bd2 Merge pull request #3713 from pipecat-ai/filipi/smallwebrtc_8khz 
Fixing smallwebrtc transport input audio resampling logic.
 2026-02-11 11:58:32 -05:00
filipi87
0c3e59ed61 Adding changelog entry for the SmallWebRTCTransport fix. 2026-02-11 13:07:52 -03:00
filipi87
ec2b38dc29 Fixing smallwebrtc transport input audio resampling logic. 2026-02-11 13:01:25 -03:00
Mark Backman
0574167fbd Merge pull request #3709 from pipecat-ai/mb/fix-quickstart-pcc-deploy 
Fix quickstart pcc-deploy.toml
 2026-02-10 22:19:37 -05:00
Mark Backman
972ad93e18 Fix quickstart pcc-deploy.toml 2026-02-10 22:17:09 -05:00
Mark Backman
ac53594967 Merge pull request #3708 from pipecat-ai/mb/fix-quickstart-pyproject 
Fix quickstart pyproject.toml
 2026-02-10 22:09:49 -05:00
Mark Backman
b063d9d43b Fix quickstart pyproject.toml 2026-02-10 22:06:38 -05:00
Mark Backman
48e93beadf Merge pull request #3705 from pipecat-ai/mb/quickstart-0.0.102 
Update quickstart for 0.0.102
 2026-02-10 21:57:33 -05:00
Aleix Conchillo Flaqué
640940a41a Merge pull request #3704 from pipecat-ai/changelog-0.0.102 
Release 0.0.102 - Changelog Update
v0.0.102 		2026-02-10 18:31:30 -08:00
aconchillo
f1e2001a4e Update changelog for version 0.0.102 2026-02-10 18:28:21 -08:00
Aleix Conchillo Flaqué
12dc6c0b9e Merge pull request #3707 from pipecat-ai/aleix/fix-openai-stream-close-compat 
fix(openai): use compatible stream closing for non-OpenAI providers
 2026-02-10 18:26:18 -08:00
Aleix Conchillo Flaqué
93f4402198 Update stream close test to match new _closing helper 2026-02-10 18:19:57 -08:00
Aleix Conchillo Flaqué
f3eb5b30a0 Add changelog for #3707 2026-02-10 18:01:29 -08:00
Aleix Conchillo Flaqué
18aad05a7c fix(openai): use compatible stream closing for non-OpenAI providers 
OpenAI's AsyncStream uses close() while async generators (e.g. from
OpenPipe) use aclose(). Replace direct async-with on the stream with a
helper that handles both protocols.
 2026-02-10 17:59:21 -08:00
Mark Backman
883b24f577 Update quickstart for 0.0.102 2026-02-10 18:14:04 -05:00
Mark Backman
17ab9c425f Merge pull request #3675 from pipecat-ai/mb/elevenlabs-realtime-send-silence 
Add silence-based keepalive to WebsocketSTTService
 2026-02-10 18:03:38 -05:00
Mark Backman
2f5e61ac55 Add silence-based keepalive to WebsocketSTTService 
Adds opt-in keepalive_timeout and keepalive_interval params to
WebsocketSTTService. When enabled, a background task sends silent audio
(or a service-specific protocol message) when the connection has been
idle, preventing server-side timeout disconnects.

Subclasses override _send_keepalive(silence) to wrap the silence in
their wire format. The default sends raw PCM bytes.

Enables keepalive for ElevenLabs (10s), Gladia (20s), and Soniox (1s),
replacing their per-service custom keepalive tasks.
 2026-02-10 17:58:47 -05:00
Aleix Conchillo Flaqué
1128c5b7fb Merge pull request #3702 from pipecat-ai/aleix/add-missing-local-smartturn-dependency 
pyproject: add local smartturn as a default dependency
 2026-02-10 14:34:43 -08:00
Aleix Conchillo Flaqué
a9a5edd8ca pyproject: add local smartturn as a default dependency 2026-02-10 14:32:32 -08:00
Filipi da Silva Fuchter
a98c884e31 Merge pull request #3621 from pipecat-ai/filipi/context_compressure 
Context summarization feature implementation
 2026-02-10 17:04:47 -05:00
filipi87
2475697955 Changelog entries for context summarization 2026-02-10 18:59:12 -03:00
filipi87
ba242d4875 Context summarization example with Google 2026-02-10 18:59:03 -03:00
filipi87
5deb80932b Context summarization example with OpenAI 2026-02-10 18:58:55 -03:00
filipi87
4a00e6829f Automated tests for the context summarizer. 2026-02-10 18:58:44 -03:00
filipi87
9d89afa7d4 Automated tests for the context summarization feature. 2026-02-10 18:58:33 -03:00
filipi87
92b6ecd945 New Claude skill to help refactor and cleanup the code. 2026-02-10 18:58:22 -03:00
filipi87
314d074c61 Context summarization feature implementation. 2026-02-10 18:58:12 -03:00
Filipi da Silva Fuchter
9c627e7292 Merge pull request #3653 from pipecat-ai/filipi/heygen_lite 
HeyGen improvements.
 2026-02-10 12:12:22 -05:00
Filipi da Silva Fuchter
ad179b0852 Merge pull request #3584 from pipecat-ai/filipi/speak_frame 
TTS services improvements.
 2026-02-10 12:11:47 -05:00
filipi87
5128089d42 Add changelog entries for PR #3653. 2026-02-10 14:02:32 -03:00
filipi87
87a79df048 Updating the heygen examples to use sandbox by default. 2026-02-10 14:02:20 -03:00
filipi87
24f90715e3 Use LITE as the default mode, and add support for video_settings and is_sandbox in LiveAvatarNewSessionRequest. 2026-02-10 14:02:09 -03:00
filipi87
e00b98343e Changelog entries for TTS context tracking 2026-02-10 11:37:21 -03:00
filipi87
ad1bec4583 Updated openai example to use on_tts_request and append_to_text. 2026-02-10 11:28:35 -03:00
filipi87
a47d7f98ee Refactored all 30+ TTS service implementations to support context tracking 2026-02-10 11:28:08 -03:00
filipi87
19cd242261 Added TTS context tracking system to trace audio generation through the pipeline. 2026-02-10 11:27:58 -03:00
filipi87
9bb712a47b Simplified universal context aggregators, _handle_text() to only check frame.append_to_context instead of also checking self._started 2026-02-10 11:27:30 -03:00
filipi87
1dccbe7c0b Simplified context aggregators, _handle_text() to only check frame.append_to_context instead of also checking self._started 2026-02-10 11:27:13 -03:00
Mark Backman
2dd3e2f1e7 Merge pull request #3697 from pipecat-ai/mb/soniox-rt-4 
Update SonioxSTTService default model to stt-rt-v4
 2026-02-10 09:24:39 -05:00
filipi87
f206aaa28d - Added context_id field to all TTS-related frames (TTSAudioRawFrame, TTSStartedFrame, TTSStoppedFrame, AggregatedTextFrame, TTSTextFrame) 
- Added append_to_context parameter to TTSSpeakFrame for conditional LLM context addition
 2026-02-10 11:22:26 -03:00
Mark Backman
60e42f5690 Merge pull request #3701 from pipecat-ai/mb/changelog-3700 2026-02-10 09:19:42 -05:00
Mark Backman
88e981c013 Set vad_force_turn_endpoint to False in SonioxSTTService 2026-02-10 09:16:03 -05:00
Mark Backman
7bd8dfe898 Add changelog for PR 3700 2026-02-10 08:20:03 -05:00
Mark Backman
83039a1a35 Merge pull request #3700 from ashotbagh/chore/async-migration 
chore: update Async API URL and default model
 2026-02-10 08:17:04 -05:00
Ashot
28e8b61eb4 chore: update Async API URL and default model 2026-02-10 15:23:51 +04:00
Mark Backman
d47d95e1f0 Update SonioxSTTService default model to stt-rt-v4 2026-02-09 23:48:08 -05:00