Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1129 commits
Select commit Hold shift + click to select a range
c9aaa46
Mentioning the recent SarvamTTSService changes in the changelog.
filipi87 Aug 26, 2025
76eef83
Removing watchdog from SarvamTTSService.
filipi87 Aug 26, 2025
32f9e48
add missing import asyncio
geluso Aug 27, 2025
8250c38
AWSPollyTTSService: allow setting auth credentials through provider c…
markbackman Aug 25, 2025
facfaa2
AWSBedrockLLMService: Allow setting auth credentials via env vars
markbackman Aug 25, 2025
3f66acf
Merge pull request #2520 from geluso/bugfix-missing-asyncio-import
markbackman Aug 27, 2025
86a37d8
Add changelog entry for SentryMetrics missing import fix
markbackman Aug 27, 2025
fc3d84d
Merge pull request #2501 from pipecat-ai/mb/aws-tts-more-flexible-auth
markbackman Aug 27, 2025
61a333c
Update quickstart to use pcc docker command
markbackman Aug 27, 2025
06f7a92
fix to `finally` statement
sam-s10s Aug 27, 2025
cc5557e
changelog
sam-s10s Aug 27, 2025
7ef6893
Merge pull request #2523 from sam-s10s/fix/connection-none
markbackman Aug 27, 2025
6074af6
Merge pull request #2521 from pipecat-ai/mb/update-quickstart-pcc-docker
markbackman Aug 27, 2025
f7d9f32
Cartesia: update speed InputParam
markbackman Aug 27, 2025
74af2b6
DailyTransport: fix sending DTMF tones
aconchillo Aug 27, 2025
41d40f9
DailyTransport: make sure we have a client before joining/leaving
aconchillo Aug 27, 2025
2613da1
PipelineTask: increase CANCEL_TIMEOUT_SECS to 20
aconchillo Aug 27, 2025
3e79ef4
Merge pull request #2525 from pipecat-ai/aleix/daily-fix-send-dtmf
aconchillo Aug 27, 2025
cd3563b
unify get_messages_for_logging()
aconchillo Aug 26, 2025
3d09f9a
Merge pull request #2524 from pipecat-ai/mb/cartesia-speed
markbackman Aug 27, 2025
1f5888b
Merge pull request #2517 from pipecat-ai/aleix/unify-get-messages-for…
aconchillo Aug 27, 2025
2bdca8d
RTVIProcessor: make check sure client version is set
aconchillo Aug 26, 2025
5e12134
Merge pull request #2516 from pipecat-ai/aleix/rtvi-client-version-check
aconchillo Aug 27, 2025
2a0780e
PipelineTask: wait for StartFrame to reach end of pipeline
aconchillo Aug 27, 2025
3c4454a
Merge pull request #2526 from pipecat-ai/aleix/pipeline-task-wait-for…
aconchillo Aug 27, 2025
e48c9fc
pyproject: update daily-python to 0.19.8
aconchillo Aug 27, 2025
d9837dd
Merge pull request #2527 from pipecat-ai/aleix/daily-python-0.19.8
aconchillo Aug 27, 2025
5803936
TextFrame: add skip_tts field
aconchillo Aug 26, 2025
16f57be
LLMConfigureOutputFrame: allow configuring LLM output
aconchillo Aug 26, 2025
eb248fe
add skip_tts to LLMFullResponseStartFrame/LLMFullResponseEndFrame
aconchillo Aug 26, 2025
e384ca9
Merge pull request #2512 from pipecat-ai/aleix/textframe-skip-tts
aconchillo Aug 27, 2025
189749b
Add `LLMRunFrame` to trigger an LLM response, replacing `context_aggr…
kompfner Aug 26, 2025
a74231f
Merge pull request #2515 from pipecat-ai/pk/llm-run-frame
kompfner Aug 28, 2025
64f2135
examples(14f): use default models
aconchillo Aug 28, 2025
5ebcea2
scripts(eval): change "result" function call parameter
aconchillo Aug 28, 2025
275c8b5
MistralLLMService: fix build_chat_completion_params()
aconchillo Aug 28, 2025
d67cece
update CHANGELOG for 0.0.82
aconchillo Aug 28, 2025
77c3407
Merge pull request #2531 from pipecat-ai/aleix/pipecat-0.0.82
aconchillo Aug 28, 2025
a5c5e06
move pipecat.frames.frames.KeypadEntry to pipecat.audio.dtmf.types.Ke…
aconchillo Aug 28, 2025
79be069
make sure warnings are always displayed
aconchillo Aug 28, 2025
5787743
audio(dtmf): added DTMF audio files and load_dtmf_audio()
aconchillo Aug 28, 2025
0e01ac8
BaseOutputTransport: implement generic write_dtmf()
aconchillo Aug 28, 2025
f03deb6
DailyTransport: remove send_dtmf() and write_dtmf()
aconchillo Aug 28, 2025
ea368e4
scripts(dtmf): added generate_dtmf.sh to generate DTMF wav files
aconchillo Aug 28, 2025
c1b8d2a
Merge pull request #2532 from pipecat-ai/aleix/universal-dtmf-support
aconchillo Aug 29, 2025
1a1d5a1
feat: add missing config params
Aug 29, 2025
633dd69
feat: add logging for pipecat version and session url
Aug 29, 2025
edc8cc1
remove sample_rate from GladiaInputParams
Aug 29, 2025
25b595e
add suggestions
Aug 29, 2025
e06bd60
update flush operation in flush audio function under rime tts
gokuljs Aug 29, 2025
b5a644d
PipelineTask: cleanup observers
aconchillo Aug 29, 2025
e3f2faa
Merge branch 'main' of github.com:rimelabs/pipecat into rime-flush-au…
gokuljs Aug 29, 2025
60c070e
update mem0 integration for reduced latency and better performance
parshvadaftari Aug 29, 2025
399f8de
audio(dtmf): use longer tones and longer gaps
aconchillo Aug 29, 2025
81325be
Merge pull request #2540 from pipecat-ai/aleix/dtmf-tones-slower
aconchillo Aug 29, 2025
bd7d934
frames: remove StopInterruptionFrame
aconchillo Aug 29, 2025
8b351f5
pyproject: update pyright and ruff
aconchillo Aug 29, 2025
972546b
Add IVR navigation (#2529)
markbackman Aug 30, 2025
bbcf35d
Add Extensions to reference docs generation
markbackman Aug 30, 2025
d567622
Fix docs build errors
markbackman Aug 30, 2025
776aafd
Merge pull request #2534 from pipecat-ai/aleix/pyright-1.1.404
aconchillo Aug 30, 2025
93a8ea3
Merge pull request #2543 from pipecat-ai/mb/docs-extensions
markbackman Aug 30, 2025
7cf099e
Merge pull request #2541 from parshvadaftari/user/parshva/update_mem0
markbackman Aug 30, 2025
2ee481d
feat: add voice cloning and speaking rate to GoogleTTSService
manishkjs1 Aug 30, 2025
1f49de5
Merge pull request #2542 from pipecat-ai/aleix/remove-stop-interrupti…
aconchillo Aug 31, 2025
83b90da
Merge pull request #2537 from pipecat-ai/aleix/pipeline-task-cleanup-…
aconchillo Aug 31, 2025
802c5d0
update changelog
Sep 1, 2025
5f80174
Add changelog entry for RimeTTSService flush_audio API update
gokuljs Sep 1, 2025
64486ef
Merge pull request #2536 from gladiaio/PLA-38-missing-config-parameters
markbackman Sep 1, 2025
472efa2
ruff format fix
gokuljs Sep 1, 2025
447e3b2
Update uv.lock for quickstart
markbackman Sep 2, 2025
547b126
Update required pipecat-ai version for quickstart
markbackman Sep 2, 2025
e1477e7
Merge pull request #2538 from rimelabs/rime-flush-audio-update
markbackman Sep 2, 2025
37e1551
Merge pull request #2555 from pipecat-ai/mb/update-uv-lock-quickstart
markbackman Sep 2, 2025
d0c97d3
Add mem0 changelog entry
markbackman Aug 30, 2025
cfe1126
Merge pull request #2546 from pipecat-ai/mb/update-changelog-mem0
markbackman Sep 2, 2025
dea7c22
Fixed an issue where the pipeline could freeze.
filipi87 Sep 2, 2025
0d8ab7a
Merge pull request #2552 from pipecat-ai/filipi/freeze_issues
filipi87 Sep 2, 2025
8ecece2
Add AIC SDK audio filter
iCorv Aug 18, 2025
c1ce3d7
bumped aic-sdk version to v1.0.1 with minor changes
iCorv Aug 21, 2025
0386599
Added Daily SIP room creation utility (#2560)
markbackman Sep 2, 2025
fdcd14d
updated CHANGELOG with AICFilter and fix deprecations
aconchillo Sep 2, 2025
ce7a051
Merge pull request #2562 from pipecat-ai/aleix/ai-coustics-speech-enh…
aconchillo Sep 2, 2025
49c1f0b
Fixed SmallWebRTCTransport to not use mid to decide if the transceive…
filipi87 Sep 2, 2025
8fbd9b5
Added support for WhatsApp User-initiated Calls.
filipi87 Sep 2, 2025
7f1100b
Merge pull request #2513 from pipecat-ai/filipi/whatsapp
filipi87 Sep 2, 2025
aeb9f1f
transports: reorganize module
aconchillo Sep 2, 2025
0a3e988
fix timeout handling in AWSBedrockLLMService
ezisezis Sep 3, 2025
2b28636
Add MISTRAL_API_KEY to env.example
kompfner Sep 2, 2025
b22bdff
Add support for universal `LLMContext` to Azure LLM service
kompfner Sep 2, 2025
d45fbd5
Add support for universal `LLMContext` to Cerebras LLM service
kompfner Sep 2, 2025
2dbd17d
Fix Cerebras function calling example
kompfner Sep 2, 2025
2b00d37
Add support for universal `LLMContext` to DeepSeek LLM service
kompfner Sep 2, 2025
f8e13a8
Fix Fireworks AI function calling example
kompfner Sep 2, 2025
da18d0a
Add support for universal `LLMContext` to Fireworks AI LLM service
kompfner Sep 2, 2025
d8882bc
Add support for universal `LLMContext` to Google Vertex AI LLM service
kompfner Sep 2, 2025
b4e1051
Add support for universal `LLMContext` to Grok LLM service
kompfner Sep 2, 2025
34f823b
Add support for universal `LLMContext` to Groq LLM service
kompfner Sep 2, 2025
ac62183
Add NVIDIA_API_KEY to env.example
kompfner Sep 2, 2025
d740bab
Add support for universal `LLMContext` to NVIDIA NIM LLM service
kompfner Sep 2, 2025
0c32cc2
Add support for universal `LLMContext` to OpenPipe LLM service
kompfner Sep 2, 2025
ec138b9
Add support for universal `LLMContext` to OpenRouter LLM service
kompfner Sep 2, 2025
5bc0e49
Add support for universal `LLMContext` to Perplexity LLM service
kompfner Sep 2, 2025
d9ea025
Add support for universal `LLMContext` to Ollama LLM service
kompfner Sep 2, 2025
b24eb76
Add QWEN_API_KEY to env.example
kompfner Sep 2, 2025
91a3f63
Add support for universal `LLMContext` to Qwen LLM service
kompfner Sep 2, 2025
e04f421
Add support for universal `LLMContext` to SambaNova LLM service
kompfner Sep 2, 2025
6838bc1
Add a few missing `LLMContext` type hints
kompfner Sep 2, 2025
7cb372e
Add support for universal `LLMContext` to Together.ai LLM service
kompfner Sep 2, 2025
9b21611
Remove `supports_universal_context` gate from OpenAI-library-based LL…
kompfner Sep 2, 2025
def1cf1
Update CHANGELOG with entry about expanded support among LLM services…
kompfner Sep 2, 2025
b9748b1
Merge pull request #2563 from pipecat-ai/pk/expand-universal-llm-cont…
kompfner Sep 3, 2025
3c4694a
Fix docs generation before 0.0.83 release
markbackman Sep 3, 2025
8b95d74
Merge pull request #2571 from pipecat-ai/mb/fix-docs-0.0.83
markbackman Sep 3, 2025
d19170d
Merge pull request #2565 from pipecat-ai/aleix/reorganize-transports
aconchillo Sep 3, 2025
83f64ec
example 07s: minor typo updates
vipyne Sep 3, 2025
c71cec0
ParallelPipeline: wait for CancelFrame in all branches
aconchillo Sep 3, 2025
b522964
DeepgramSTTService: remove raising CancelledError
aconchillo Sep 3, 2025
052ffe8
fix: Specify frame direction in 06a push_frame
markbackman Sep 3, 2025
d8ac6f2
fix: update default Cerebras model to Qwen 3 32B
joyceerhl Sep 3, 2025
8e5880b
Merge pull request #2575 from pipecat-ai/mb/fix-foundational-frame-di…
markbackman Sep 3, 2025
f56be93
Merge pull request #2572 from pipecat-ai/aleix/deepgram-disconnect-task
aconchillo Sep 3, 2025
09d6ec1
introduce and push UserSpeakingFrame upstream/downstream
aconchillo Sep 3, 2025
a001f6f
Switch to GPT-OSS-120B
joyceerhl Sep 3, 2025
eba006d
Fix nits
joyceerhl Sep 3, 2025
c64bc5a
Merge pull request #2576 from joyceerhl/joyce/cerebras-default
markbackman Sep 3, 2025
977a57c
Add 14k (CerebrasLLMService) to release evals
markbackman Sep 3, 2025
5a4c6b9
BaseInputTransport: push UserStartedSpeakingFrame/UserStoppedSpeaking…
aconchillo Sep 3, 2025
978f644
Merge pull request #2578 from pipecat-ai/aleix/user-speaking-frame
aconchillo Sep 3, 2025
99e237b
Fixed an issue where messages received from the transport were always…
filipi87 Sep 3, 2025
001a2d3
Merge pull request #2579 from pipecat-ai/filipi/input_message
filipi87 Sep 3, 2025
d146170
Merge pull request #2580 from pipecat-ai/mb/add-cerebras-evals
aconchillo Sep 3, 2025
f0baff9
update CHANGELOG for 0.0.83
aconchillo Sep 3, 2025
0fab56f
Merge pull request #2577 from pipecat-ai/aleix/pipecat-0.0.83
aconchillo Sep 3, 2025
a26647c
fix: openai image generator now initiates URLImageRawFrame with corre…
sassanh Sep 4, 2025
daf7fed
feat(asyncai): add multilingual TTS support
Sep 4, 2025
a1c6ad5
Merge pull request #2585 from ashotbagh/feat/asyncai-multilingual-sup…
markbackman Sep 4, 2025
586586f
Update quickstart pyproject to use 0.0.83
markbackman Sep 4, 2025
595a7c7
Merge pull request #2587 from pipecat-ai/mb/update-quickstart-0.0.83
markbackman Sep 4, 2025
0d9e119
Merge pull request #2583 from sassanh/main
aconchillo Sep 4, 2025
ee3b023
update CHANGELOG with OpenAIImageGenService fix
aconchillo Sep 4, 2025
f2b50c1
Merge pull request #2573 from pipecat-ai/vp-minor-fixes-07s
aconchillo Sep 4, 2025
b609b02
Merge pull request #2568 from ezisezis/fix-bedrock-timeouts
aconchillo Sep 4, 2025
65298ab
update CHANGELOG with AWSBedrockLLMService fix
aconchillo Sep 4, 2025
e359780
AWSNovaSonicLLMService: pre-load audio cue in the constructor
aconchillo Aug 30, 2025
2df2311
Add foundational example using Anthropic with universal `LLMContext`
kompfner Sep 3, 2025
5c574ea
Add support for universal `LLMContext` to Anthropic LLM service
kompfner Sep 3, 2025
b56ff86
Minor refactor of `AnthropicLLMAdapter` cache-control-marker-adding l…
kompfner Sep 4, 2025
986160c
Fix a bug where the Anthropic adapter's merge-consecutive-messages-wi…
kompfner Sep 4, 2025
d620502
Trivial cleanup
kompfner Sep 4, 2025
c11b207
Add Anthropic to CHANGELOG list of services newly supporting runtime …
kompfner Sep 4, 2025
b2e9fd9
Rename Anthropic `enable_prompt_caching_beta` parameter to just `enab…
kompfner Sep 4, 2025
dc3412b
Bump a deprecation to 0.0.84, as 0.0.83 just shipped
kompfner Sep 4, 2025
ba5ebfa
Fixed subtle CHANGELOG conflict after release of 0.0.83: universal `L…
kompfner Sep 4, 2025
0826d72
Add deprecation warning for using `enable_prompt_caching_beta` param
kompfner Sep 4, 2025
f72ca2f
Remove unnecessary `system_instruction` argument from `run_inference(…
kompfner Sep 4, 2025
6e734a3
Fix a bug in `AWSBedrockLLMService.run_inference()`; it was expecting…
kompfner Sep 4, 2025
3d850e8
Merge pull request #2574 from pipecat-ai/pk/expand-universal-llm-cont…
kompfner Sep 4, 2025
4699ee8
docs: add docstring for voice_cloning_key and update CHANGELOG
manishkjs1 Sep 4, 2025
246f9f3
Raise an error when attempting to use Gemini Multimodal Live with uni…
kompfner Sep 4, 2025
516f0e0
Merge pull request #2590 from pipecat-ai/pk/gemini-multimodal-live-do…
kompfner Sep 5, 2025
5477dfc
Improving HeyGen example video quality.
filipi87 Sep 5, 2025
dc2e1d4
Fix Anthropic tool-less usage
kompfner Sep 5, 2025
2944296
Merge pull request #2597 from pipecat-ai/pk/fix-anthropic-tool-less-u…
kompfner Sep 5, 2025
64b4c65
Merge pull request #2595 from pipecat-ai/filipi/heygen_quality
filipi87 Sep 5, 2025
fbe4338
DTMF: Add support for native DTMF implementation where available
markbackman Sep 5, 2025
25747a0
Merge pull request #2599 from pipecat-ai/mb/fix-daily-dtmf
markbackman Sep 5, 2025
2f44f88
LiveKitTransport: Add support to send DTMF
markbackman Sep 5, 2025
ea3f7e3
Merge pull request #2600 from pipecat-ai/mb/livekit-dtmf
markbackman Sep 5, 2025
f8b2ab6
pyproject: update daily-python to 0.19.9
aconchillo Sep 6, 2025
b9c96fd
Merge pull request #2601 from pipecat-ai/aleix/daily-python-0.19.9
aconchillo Sep 6, 2025
070690e
update CHANGELOG for 0.0.84
aconchillo Sep 6, 2025
85d8282
Merge pull request #2602 from pipecat-ai/aleix/pipecat-0.0.84
aconchillo Sep 6, 2025
13b73d4
feat: Add support for pipecat video stream; fix the bug of duplicate …
alexzhou-autoark Sep 6, 2025
d643258
fix: fix format and lint by ruff
alexzhou-autoark Sep 6, 2025
dbc52bc
Remove uv.lock from quickstart
markbackman Sep 6, 2025
7366b1a
adds missing InterimTranscriptionFrame import
TheNotary Sep 6, 2025
46deaad
scripts(evals): allow user to talk and only eval when needed
aconchillo Sep 7, 2025
a537382
Add OpenAIRealtimeLLMService, AzureRealtimeLLMService (#2596)
markbackman Sep 7, 2025
6edb6fe
Merge pull request #2606 from pipecat-ai/mb/quickstart-lockfile
markbackman Sep 7, 2025
6a6a63a
Merge pull request #2607 from pipecat-ai/aleix/scripts-evals-improve-…
aconchillo Sep 8, 2025
d7794ab
audio(filters): deprecate NoisereduceFilter
aconchillo Sep 7, 2025
1cccb97
Merge pull request #2608 from pipecat-ai/aleix/deprecate-noisereducef…
aconchillo Sep 8, 2025
daee1dd
Apply additional fixups to context messages to meet Mistral-specific …
kompfner Sep 8, 2025
0bb7df7
Remove stray debugging message
kompfner Sep 8, 2025
e65385c
Tweak the Mistral-specific context messages fixup logic to handle the…
kompfner Sep 8, 2025
ac4d335
Merge pull request #2613 from pipecat-ai/pk/mistral-message-fixups
kompfner Sep 8, 2025
0f1cf81
README: update clients' table
aconchillo Sep 8, 2025
d55133a
Merge pull request #2604 from alexyzhou/feature/livekit_video_and_bug…
aconchillo Sep 8, 2025
aa471a4
update CHANGELOG with LiveKitTransport updates
aconchillo Sep 8, 2025
f3a4b41
Remove `VisionImageRawFrame`, which was previously being handled dire…
kompfner Sep 5, 2025
a3e65ab
The `VisionImageRawFrame` removal and corresponding `VisionImageFrame…
kompfner Sep 8, 2025
623c660
Remove debugging comment
kompfner Sep 8, 2025
1c3e4e3
Minor fix to AWS Bedrock console logging to handle image messages in …
kompfner Sep 8, 2025
38f6e33
Merge pull request #2598 from pipecat-ai/pk/deprecate-vision-image-ra…
kompfner Sep 8, 2025
f4d6715
Add foundational example using AWS Bedrock with universal LLMContext
kompfner Sep 9, 2025
75f9914
Add support for universal LLMContext to AWS Bedrock LLM service
kompfner Sep 9, 2025
176573c
Add to CHANGELOG AWS Bedrock's support for universal `LLMContext`
kompfner Sep 9, 2025
fe79de8
When converting universal `LLMContext` messages to AWS Bedrock expect…
kompfner Sep 9, 2025
8ccd220
Add universal `LLMContext` support to `AWSBedrockLLMService.run_infer…
kompfner Sep 9, 2025
fedb8a2
Update 12d example to use `LLMContext`, now that AWS Bedrock supports it
kompfner Sep 9, 2025
e8f60c7
Handle missing rawResponse in transcription messages (#2623)
jamsea Sep 10, 2025
f4938e0
fix: 13 foundational examples now push frames from TranscriptionLogger
markbackman Sep 10, 2025
dd6ff78
Merge pull request #2628 from pipecat-ai/mb/fix-13-push-frame
markbackman Sep 10, 2025
9083254
Merge pull request #2614 from pipecat-ai/aleix/readme-client-sdks-table
aconchillo Sep 10, 2025
b31322e
Merge pull request #2619 from pipecat-ai/pk/aws-universal-context
kompfner Sep 11, 2025
8e8e427
Add to and from phone information to the development runner
markbackman Sep 10, 2025
a2e76bc
Smart Turn V3 support
marcus-daily Aug 18, 2025
3e9fc7b
Update onnxruntime version
marcus-daily Sep 11, 2025
818352a
Formatting
marcus-daily Sep 11, 2025
a9b53dc
Update inference session options
marcus-daily Sep 11, 2025
66ce5fe
Ruff fixes
marcus-daily Sep 11, 2025
e27b236
frames: add new TaskFrame
aconchillo Sep 9, 2025
9d9f10a
frames: StartInterruptionFrame is deprecated, use InterruptionFrame
aconchillo Sep 9, 2025
8249b01
frames: BotInterruptionFrame is deprecated, use InterruptionTaskFrame
aconchillo Sep 9, 2025
0b21f8a
FrameProcessor: add push_interruption_task_frame_and_wait()
aconchillo Sep 9, 2025
9b3f692
Merge pull request #2621 from pipecat-ai/aleix/interruption-task-frame
aconchillo Sep 11, 2025
6a717fb
Updating the README to reflect that:
kompfner Sep 11, 2025
fafcd79
OpenAITTSService: add speed arg
markbackman Sep 11, 2025
d6543d2
uv.lock update for Smart Turn v3
kompfner Sep 11, 2025
a4023d3
Update evals to include examples that exercise the universal `LLMCont…
kompfner Sep 11, 2025
aff11f5
Fix missing import in llm_response_universal.py
kompfner Sep 11, 2025
dac58de
Merge pull request #2636 from pipecat-ai/pk/uv-lock-update-for-smart-…
kompfner Sep 11, 2025
74b38b5
tests(utils): allow passing PipelineParams to run_test()
aconchillo Sep 11, 2025
57add41
tests: add unit test for MinWordsInterruptionStrategy
aconchillo Sep 11, 2025
d2f210e
Bundle Smart Turn v3 with Pipecat
marcus-daily Sep 11, 2025
be28d3f
Merge pull request #2637 from pipecat-ai/pk/llm-context-evals-and-bug…
kompfner Sep 11, 2025
3c271da
Merge pull request #2633 from pipecat-ai/pk/uv-readme-updates
kompfner Sep 11, 2025
37b6198
Merge pull request #2635 from pipecat-ai/mb/openai-tts-speed
markbackman Sep 11, 2025
c26d336
Merge pull request #2545 from pipecat-ai/aleix/aws-nova-sonic-pre-loa…
aconchillo Sep 11, 2025
0c30cc6
Merge pull request #2547 from manishkjs/feat/google-tts-voice-cloning
aconchillo Sep 11, 2025
05dc2fa
updated CHANGELOG.md with GoogleTTSService updates
aconchillo Sep 11, 2025
fafdada
Merge pull request #2473 from TheNotary/adds-interim-transcription-fr…
aconchillo Sep 11, 2025
ab4364b
update CHANGELOG and fix formatting
aconchillo Sep 11, 2025
384814e
Merge pull request #2456 from a6kme/patch-1
aconchillo Sep 11, 2025
89f7e7d
update CHANGELOG with BaseOutputTransport fix
aconchillo Sep 11, 2025
2a24061
examples(07ad): remove deprecated user_continuous_stream
aconchillo Sep 12, 2025
0190812
Merge pull request #2639 from pipecat-ai/aleix/min-words-interruption…
aconchillo Sep 12, 2025
d595676
Add custom data handling for Twilio
markbackman Sep 11, 2025
99cfcb1
Parsed custom data from Plivo extraHeaders
markbackman Sep 11, 2025
e5ed042
Remove to/from data from Plivo, as it will rely on body information
markbackman Sep 12, 2025
22633a6
Update changelog
markbackman Sep 12, 2025
2f496ac
Add optional body parameter to WebsocketRunnerArguments
markbackman Sep 12, 2025
1b2a5df
Merge pull request #2622 from pipecat-ai/mb/call-data-runner
aconchillo Sep 12, 2025
0f2b7bc
examples(foundational): fix 19b-openai-realtime-beta-text
aconchillo Sep 12, 2025
82478be
scripts(evals): add 19b-openai-realtime-text
aconchillo Sep 12, 2025
c2df6c8
update CHANGELOG for 0.0.85
aconchillo Sep 12, 2025
d8cd28b
Merge pull request #2640 from pipecat-ai/aleix/pipecat-0.0.85
aconchillo Sep 12, 2025
06ce682
Adding force_cancel
lzaidi-homelight Sep 15, 2025
2d0f1ab
applying websocket disconnect infinite loop error fix
lzaidi-homelight Oct 15, 2025
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
The table of contents is too big for display.
Diff view
Diff view
  •  
  •  
  •  
60 changes: 0 additions & 60 deletions .github/workflows/android.yaml

This file was deleted.

34 changes: 15 additions & 19 deletions .github/workflows/build.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -21,24 +21,20 @@ jobs:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Set up Python
id: setup_python
uses: actions/setup-python@v4

- name: Install uv
uses: astral-sh/setup-uv@v3
with:
python-version: '3.10'
- name: Setup virtual environment
run: |
python -m venv .venv
- name: Install basic Python dependencies
run: |
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -r dev-requirements.txt
version: "latest"

- name: Set up Python
run: uv python install 3.10

- name: Install development dependencies
run: uv sync --group dev

- name: Build project
run: |
source .venv/bin/activate
python -m build
- name: Install project and other Python dependencies
run: |
source .venv/bin/activate
pip install --editable .
run: uv build

- name: Install project in editable mode
run: uv pip install --editable .
37 changes: 15 additions & 22 deletions .github/workflows/coverage.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -18,35 +18,28 @@ jobs:
steps:
- name: Checkout repo
uses: actions/checkout@v4
- name: Set up Python
id: setup_python
uses: actions/setup-python@v4
with:
python-version: "3.10"
- name: Cache virtual environment
uses: actions/cache@v3

- name: Install uv
uses: astral-sh/setup-uv@v3
with:
# We are hashing dev-requirements.txt and test-requirements.txt which
# contain all dependencies needed to run the tests.
key: venv-${{ runner.os }}-${{ steps.setup_python.outputs.python-version}}-${{ hashFiles('dev-requirements.txt') }}-${{ hashFiles('test-requirements.txt') }}
path: .venv
version: "latest"

- name: Set up Python
run: uv python install 3.12

- name: Install system packages
id: install_system_packages
run: |
sudo apt-get install -y portaudio19-dev
- name: Setup virtual environment
run: |
python -m venv .venv
- name: Install basic Python dependencies

- name: Install dependencies
run: |
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -r dev-requirements.txt -r test-requirements.txt
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain

- name: Run tests with coverage
run: |
source .venv/bin/activate
coverage run
coverage xml
uv run coverage run
uv run coverage xml

- name: Upload coverage to Codecov
uses: codecov/codecov-action@v5
with:
Expand Down
35 changes: 16 additions & 19 deletions .github/workflows/format.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -17,30 +17,27 @@ concurrency:

jobs:
ruff-format:
name: "Formatting checker"
name: "Code quality checks"
runs-on: ubuntu-latest
steps:
- name: Checkout repo
uses: actions/checkout@v4
- name: Set up Python
uses: actions/setup-python@v4

- name: Install uv
uses: astral-sh/setup-uv@v3
with:
python-version: "3.10"
- name: Setup virtual environment
run: |
python -m venv .venv
- name: Install development Python dependencies
run: |
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -r dev-requirements.txt
version: "latest"

- name: Set up Python
run: uv python install 3.10

- name: Install development dependencies
run: uv sync --group dev

- name: Ruff formatter
id: ruff-format
run: |
source .venv/bin/activate
ruff format --diff
- name: Ruff import linter
run: uv run ruff format --diff

- name: Ruff linter (all rules)
id: ruff-check
run: |
source .venv/bin/activate
ruff check --select I
run: uv run ruff check
26 changes: 10 additions & 16 deletions .github/workflows/publish.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ on:
inputs:
gitref:
type: string
description: "what git ref to build"
description: "what git tag to build (e.g. v0.0.74)"
required: true

jobs:
Expand All @@ -17,23 +17,17 @@ jobs:
uses: actions/checkout@v4
with:
ref: ${{ github.event.inputs.gitref }}
- name: Set up Python
id: setup_python
uses: actions/setup-python@v4

- name: Install uv
uses: astral-sh/setup-uv@v3
with:
python-version: '3.10'
- name: Setup virtual environment
run: |
python -m venv .venv
- name: Install basic Python dependencies
run: |
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -r dev-requirements.txt
version: "latest"
- name: Set up Python
run: uv python install 3.10
- name: Install development dependencies
run: uv sync --group dev
- name: Build project
run: |
source .venv/bin/activate
python -m build
run: uv build
- name: Upload wheels
uses: actions/upload-artifact@v4
with:
Expand Down
25 changes: 9 additions & 16 deletions .github/workflows/publish_test.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -12,23 +12,16 @@ jobs:
with:
fetch-tags: true
fetch-depth: 100
- name: Set up Python
id: setup_python
uses: actions/setup-python@v4
- name: Install uv
uses: astral-sh/setup-uv@v3
with:
python-version: '3.10'
- name: Setup virtual environment
run: |
python -m venv .venv
- name: Install basic Python dependencies
run: |
source .venv/bin/activate
python -m pip install --upgrade pip
pip install -r dev-requirements.txt
version: "latest"
- name: Set up Python
run: uv python install 3.10
- name: Install development dependencies
run: uv sync --group dev
- name: Build project
run: |
source .venv/bin/activate
python -m build
run: uv build
- name: Upload wheels
uses: actions/upload-artifact@v4
with:
Expand All @@ -38,7 +31,7 @@ jobs:
publish-to-test-pypi:
name: "Publish to Test PyPI"
runs-on: ubuntu-latest
needs: [ build ]
needs: [build]
environment:
name: testpypi
url: https://pypi.org/p/pipecat-ai
Expand Down
61 changes: 61 additions & 0 deletions .github/workflows/python-compatibility.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,61 @@
name: Python Compatibility Test

on:
push:
branches: [main, develop]
paths: ['pyproject.toml']
pull_request:
branches: [main, develop]
paths: ['pyproject.toml']

jobs:
test-compatibility:
runs-on: ubuntu-latest
strategy:
fail-fast: false
matrix:
python-version: ['3.10.18', '3.11.13', '3.12.11', '3.13.5']

name: Python ${{ matrix.python-version }}
steps:
- name: Checkout code
uses: actions/checkout@v4

- name: Install system dependencies
run: |
sudo apt-get update
sudo apt-get install -y \
portaudio19-dev \
libcairo2-dev \
libgirepository1.0-dev \
pkg-config

- name: Install uv
uses: astral-sh/setup-uv@v4
with:
version: 'latest'

- name: Set up Python ${{ matrix.python-version }}
run: |
uv python install ${{ matrix.python-version }}
uv python pin ${{ matrix.python-version }}

- name: Test uv sync with all extras (Python < 3.13)
if: "!startsWith(matrix.python-version, '3.13.')"
run: |
uv sync --group dev --all-extras --no-extra krisp

- name: Test uv sync without PyTorch extras (Python 3.13+)
if: startsWith(matrix.python-version, '3.13.')
run: |
uv sync --group dev --all-extras \
--no-extra krisp \
--no-extra ultravox \
--no-extra local-smart-turn \
--no-extra moondream \
--no-extra mlx-whisper

- name: Verify installation
run: |
uv run python --version
uv run python -c "import pipecat; print('✅ Pipecat imports successfully')"
51 changes: 51 additions & 0 deletions .github/workflows/sync-quickstart.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,51 @@
name: Sync Quickstart to pipecat-quickstart repo

on:
push:
branches: [main]
paths:
- 'examples/quickstart/**'
workflow_dispatch: # Manual trigger

jobs:
sync-quickstart:
runs-on: ubuntu-latest
steps:
- name: Checkout main repo
uses: actions/checkout@v4
with:
fetch-depth: 0

- name: Checkout quickstart repo
uses: actions/checkout@v4
with:
repository: pipecat-ai/pipecat-quickstart
token: ${{ secrets.QUICKSTART_SYNC_TOKEN }}
path: quickstart-repo

- name: Sync files (excluding uv.lock and README.md)
run: |
# Copy all files except uv.lock and README.md
find examples/quickstart -type f \
-not -name "README.md" \
-not -name "uv.lock" \
-exec cp {} quickstart-repo/ \;

- name: Commit and push changes
run: |
cd quickstart-repo
git config user.name "GitHub Action"
git config user.email "action@github.com"
git add .

# Only commit if there are changes
if ! git diff --staged --quiet; then
git commit -m "Sync from pipecat main repo

Updated files from examples/quickstart/
Commit: ${{ github.sha }}
"
git push
else
echo "No changes to sync"
fi
Loading
Loading