wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
8,618 Commits 276 Branches 111 Tags
33e146decd5aba4e53bde6dbbfe3324cfb9f903e
Commit Graph

8618 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Mark Backman
bdeeacec51 uv.lock update 2026-03-03 10:37:35 -05:00
Mark Backman
8f04f894d5 Merge pull request #3907 from pipecat-ai/mb/update-docs-skill-new-services 2026-03-03 09:48:01 -05:00
Mark Backman
ca0ec16373 Merge pull request #3889 from ai-coustics/goedev/aic-voice-focus-and-memoryview-fix 
AIC Voice Focus version update & concurrency safety issue on audio buffer.
 2026-03-03 09:28:13 -05:00
Filipi da Silva Fuchter
150c8b92e5 Merge pull request #3848 from pipecat-ai/filipi/deepgram 
Upgrading Deepgram to version 6
 2026-03-03 09:07:10 -05:00
filipi87
0fdf7dc16a Fixing sagemaker merge conflicts. 2026-03-03 11:03:51 -03:00
filipi87
fc905a7ef5 Merge branch 'main' into filipi/deepgram 
# Conflicts:
#	src/pipecat/services/deepgram/stt_sagemaker.py
 2026-03-03 10:54:30 -03:00
Mark Backman
aca92745cd Update update-docs skill to register new services in docs.json and supported-services.mdx 
When the skill creates a new service documentation page, it now also adds
the page to docs.json navigation and the supported-services.mdx table.
 2026-03-03 08:40:12 -05:00
Aleix Conchillo Flaqué
5940731dd0 Merge pull request #3906 from pipecat-ai/changelog-0.0.104 
Release 0.0.104 - Changelog Update
v0.0.104 		2026-03-02 21:24:05 -08:00
aconchillo
62260454a2 Update changelog for version 0.0.104 2026-03-02 21:23:39 -08:00
Aleix Conchillo Flaqué
d1ad7a9580 Merge pull request #3905 from pipecat-ai/aleix/tavus-fix-callback-on-joined 
transport(tavus): fix on_joined callback
 2026-03-02 21:11:12 -08:00
Aleix Conchillo Flaqué
252f17e1ca transport(tavus): fix on_joined callback 2026-03-02 21:06:49 -08:00
Mark Backman
c79a739c85 Merge pull request #3856 from zkleb-aai/assemblyai-u3-rt-pro 
Assemblyai u3 rt pro
 2026-03-02 20:28:28 -05:00
Mark Backman
038f6a77d1 Linting 2026-03-02 20:24:30 -05:00
Aleix Conchillo Flaqué
5952ea711c update uv.lock 2026-03-02 16:42:58 -08:00
Mark Backman
aad1211a57 Merge pull request #3885 from pipecat-ai/mb/latency-breakdown 
Add latency breakdown to UserBotLatencyObserver
 2026-03-02 19:27:35 -05:00
Mark Backman
7dbb130666 Add chronological_events utility function to display UserBotLatencyObserver report 2026-03-02 19:23:42 -05:00
zack
c6c2c5ba05 Fix end_of_turn_confidence_threshold: set to 1.0 (not 0.0) for universal-streaming 
- u3-rt-pro: Does not set parameter (not used)
- universal-streaming models: Set to 1.0 to maintain fast response
- This ensures fast response time matches previous implementation
 2026-03-02 18:25:25 -05:00
Aleix Conchillo Flaqué
141b0ee014 Merge pull request #3902 from pipecat-ai/aleix/deepgram-sagemaker-move 
Move Deepgram SageMaker modules to sagemaker/ subpackage
 2026-03-02 15:25:17 -08:00
Aleix Conchillo Flaqué
303616599f Add changelog for #3902 2026-03-02 15:20:52 -08:00
Aleix Conchillo Flaqué
088eb9b01c examples: update to new sagemaker packages 2026-03-02 15:20:52 -08:00
zack
32773b42d6 Improve terminology: rename file and replace 'STT mode' with 'AssemblyAI turn detection' 
- Rename 07o-interruptible-assemblyai-stt.py -> 07o-interruptible-assemblyai-turn-detection.py
- Replace 'STT mode' with 'AssemblyAI turn detection mode' throughout codebase
- Replace 'Mode 1'/'Mode 2' with descriptive 'Pipecat turn detection'/'AssemblyAI turn detection'
- Update changelog to use 'built-in turn detection' terminology
- Addresses PR feedback about confusing terminology
 2026-03-02 18:08:46 -05:00
Mark Backman
c039e08741 Merge pull request #3900 from pipecat-ai/filipi/lemonslice 
Adding the LemonSlice transport integration
 2026-03-02 17:56:18 -05:00
zack
b449515410 Address PR review feedback: remove debug logs, fix hasattr logic, add VADAnalyzer 2026-03-02 17:54:31 -05:00
Mark Backman
aae9136df9 Review feedback 2026-03-02 17:52:39 -05:00
Aleix Conchillo Flaqué
fdeddd7c95 Add deprecation shims for moved stt_sagemaker/tts_sagemaker modules 
Re-export from the new pipecat.services.deepgram.sagemaker.{stt,tts}
paths so existing imports keep working with a deprecation warning.
 2026-03-02 14:47:17 -08:00
Aleix Conchillo Flaqué
11783520c0 services(deepgram): move stt|tts_sagemaker to sagemaker/stt|tts.py 2026-03-02 14:43:34 -08:00
filipi87
49c73bb0a3 Merge branch 'main' into filipi/lemonslice 
# Conflicts:
#	README.md
#	uv.lock
 2026-03-02 19:24:52 -03:00
filipi87
f07e55a4ed Wrap LemonSlice session creation params in LemonSliceNewSessionRequest 2026-03-02 19:15:18 -03:00
filipi87
daf14f5065 Renaming LemonSlice utils file to api. 2026-03-02 19:08:17 -03:00
filipi87
ebb794995b Changing the log levels. 2026-03-02 19:06:13 -03:00
zkleb-aai
5c2ca0ce64 Update changelog/3856.changed.md 
Co-authored-by: Mark Backman <m.backman@gmail.com>
 2026-03-02 17:04:54 -05:00
zkleb-aai
6729f4366a Update src/pipecat/services/assemblyai/stt.py 
Co-authored-by: Mark Backman <m.backman@gmail.com>
 2026-03-02 17:04:42 -05:00
zkleb-aai
7648b62e6e Update src/pipecat/services/assemblyai/stt.py 
Co-authored-by: Mark Backman <m.backman@gmail.com>
 2026-03-02 17:04:17 -05:00
filipi87
7afd7068b5 Retrieving the elevenlabs voice ID from environment variable 2026-03-02 19:02:51 -03:00
filipi87
07fdd610ca Using a default voice in case it is not provided. 2026-03-02 19:02:33 -03:00
Mark Backman
a4796a2373 Merge pull request #3898 from pipecat-ai/mb/revert-processing-metrics-deprecation 
Revert processing metrics deprecation
 2026-03-02 16:39:02 -05:00
Aleix Conchillo Flaqué
44466cfa07 Merge pull request #3896 from pipecat-ai/aleix/broadcast-interruption 
Add broadcast_interruption() to FrameProcessor
 2026-03-02 13:36:39 -08:00
Mark Backman
68d7e98f95 Add defensive comment for given_fields() usage in tracing 2026-03-02 16:33:25 -05:00
Aleix Conchillo Flaqué
741ff14d3a Rename changelog files to use PR #3896 and mark breaking change 2026-03-02 13:26:45 -08:00
Aleix Conchillo Flaqué
4a61d5bfad Add broadcast_interruption() to FrameProcessor 
Replace the round-trip push_interruption_task_frame_and_wait() mechanism
with broadcast_interruption(), which pushes an InterruptionFrame both
upstream and downstream directly from the calling processor.

This eliminates race conditions (transcription arriving before the
InterruptionFrame comes back), swallowed-event timeouts (frame blocked
before reaching the sink), and the complexity of _wait_for_interruption
flag / queue bypass / frame.complete() obligations.

- Add broadcast_interruption() to FrameProcessor
- Deprecate push_interruption_task_frame_and_wait() (delegates to new method)
- Remove event field and complete() from InterruptionFrame/InterruptionTaskFrame
- Remove _wait_for_interruption flag and all special-case logic
- Remove frame.complete() calls in stt_mute_filter and llm_response_universal
- Update all 17 call sites to use broadcast_interruption()
- Update tests
 2026-03-02 13:26:45 -08:00
Mark Backman
d0ecb3c7a8 Revert "Deprecate processing metrics (ProcessingMetricsData)" (#3852) 
This reverts commit 127b52bad5.
 2026-03-02 16:26:29 -05:00
Mark Backman
8f66272de7 Update changelog 2026-03-02 16:16:38 -05:00
Mark Backman
ff5b985009 Convert observer data models to Pydantic BaseModel with timestamps 
Enables .model_dump() serialization for Pipecat Cloud collection.
All metrics now include start_time (Unix timestamp) for timeline
plotting alongside duration_secs.
 2026-03-02 16:11:43 -05:00
Mark Backman
a738a4d82b Add function call latency tracking to LatencyBreakdown 2026-03-02 16:11:43 -05:00
Mark Backman
ddba1b84a9 Add first-bot-speech latency to UserBotLatencyObserver 
Measure time from ClientConnectedFrame to first BotStartedSpeakingFrame,
emitting a one-time on_first_bot_speech_latency event with breakdown.
 2026-03-02 16:11:43 -05:00
Mark Backman
18155b6a63 Add latency breakdown to UserBotLatencyObserver 
Add per-service latency breakdown metrics alongside existing user-to-bot
latency measurement. When enable_metrics=True, the observer now emits an
on_latency_breakdown event with TTFB, text aggregation, and user turn
duration metrics collected between VADUserStoppedSpeakingFrame and
BotStartedSpeakingFrame.

- Add LatencyBreakdown dataclass with ttfb, text_aggregation,
  user_turn_secs fields
- Accumulate MetricsFrame data during user→bot cycles
- Reset accumulators on InterruptionFrame to discard stale metrics
- Measure user_turn_secs from actual user silence (VAD timestamp -
  stop_secs) to turn release (UserStoppedSpeakingFrame)
- Filter zero-value TTFB entries from startup metric resets
- Add frame deduplication using bounded deque + set pattern
- Update example 29 with latency breakdown display
 2026-03-02 16:11:43 -05:00
Mark Backman
ac69b3441e Fix tracing to use ServiceSettings API instead of dict access 
The ServiceSettings refactor (PR #3714) changed self._settings from
dicts to dataclass subclasses, but tracing code still used .items(),
in containment, and subscript access, causing AttributeError on
every traced call. Use given_fields() for iteration and attribute
access for named fields.
 2026-03-02 16:11:43 -05:00
Mark Backman
98bd530574 Add changelog for #3881 2026-03-02 16:11:42 -05:00
Mark Backman
b1e55fd6c2 Merge pull request #3881 from pipecat-ai/mb/startup-observer 
Add StartupTimingObserver
 2026-03-02 16:07:28 -05:00
Mark Backman
dbdb54ce0f Add on_connected event handler to DailyTransport for cross-transport consistency 2026-03-02 15:44:37 -05:00