Commit Graph

4494 Commits

Author SHA1 Message Date
Mark Backman
b8d2fceced Merge pull request #2138 from pipecat-ai/mb/fix-google-llm-import-order
GoogleLLMService: Linting fixes
2025-07-03 13:26:32 -07:00
Sam Sykes
7596d71460 Speechmatics STT + multi-speaker conversations (#2036)
* initial config

* skeleton

* Added a README (to be added to).

* Payloads coming from the ASR.

* doc update

* handle the partials and finals

* enable diarization in the example

* support sending messages to pipecat pipeline

* requirements fix in README

* updated example (with amusement)

* updated example to match master

* updated docs

* support for diarization tags

* logic fix for wrapper

* Use an internal SpeechFrame for speaker_id (not user_id).

* only include speaker tags on finalised transcript (as this may skew end of utterance detection)

* updated docs

* correction to docs and updated example

* updated requirement

* Fix for using default EU server.

* Updates from PR comments.

* Refactor based on comments in the original PR.

Primary focus on documentation, naming conventions and how `user_id` is used.

* Check for SMX installed when importing.

* Variable name change

* Comment correction.

* Support for Esporanto and Uyghur

* Impoved language support

* function name change

* Locale fix

* intercept

* interim changes

* pass the pipeline task to the module for adding events to the top of the pipeline

* logging for the pipeline

* Reduce timeout for content aggregator.

* staged update

* testing with Azure

* Updated context (Azure was dropping punctuation) and using better ElevenLabs model.

* Updated to RT 0.3.0 and use OpenAI (not Azure).

* Missing OpenAI import; parameter name change for output locale validation.

* Revert to `0.2.0` of RT SDK.

* fix for assignment of `output_locale_code`.

* update Speechmatics library to 0.3.1

* new transcription example

* updated asyncio task handling

* Updated doc strings

* enable OpenTelemetry logging

* removed import from stt for __init__

* updated examples and default values

* updated examples

* prevent lock up when closing the STT connection
2025-07-03 17:25:13 -03:00
Mark Backman
096067b097 GoogleLLMService: Linting fixes 2025-07-03 13:23:13 -07:00
Aleix Conchillo Flaqué
8f6544efe2 Merge pull request #2133 from pipecat-ai/vp-changelog-fileapi
docs: add changelog line for gemini files api
2025-07-03 11:13:02 -07:00
otaqwawi
6045a8ad8c Add option to change the base URL for Google Generative AI. (#2113)
* Add option to change the base URL for Google Generative AI.
This would be useful to support private instance or gateway of the API

* fix: add proper type hints for http_options in Google LLM service
2025-07-03 11:12:35 -07:00
Aleix Conchillo Flaqué
b184d62634 Merge pull request #2134 from pipecat-ai/aleix/evals-cancel-expired-tasks
cancel expire evals tasks
2025-07-03 10:07:27 -07:00
Aleix Conchillo Flaqué
1a8d512abb scripts(evals): make sure we cancel pending tasks after timeout 2025-07-03 10:01:42 -07:00
vipyne
a62be8ea32 docs: add changelog line for gemini files api 2025-07-03 11:44:34 -05:00
Mark Backman
c230d94ff0 Merge pull request #2125 from pipecat-ai/mb/deprecate-handle-function-call-start
Add docs deprecation for handle_function_call_start
2025-07-03 12:27:17 -04:00
Aleix Conchillo Flaqué
e7b02773f5 Merge pull request #2131 from pipecat-ai/aleix/dtmf-aggregator-dangling-tasks
DtmfAggregator: cancel interruption task to avoid a dangling task
2025-07-03 08:34:50 -07:00
Aleix Conchillo Flaqué
ed83248a6b Merge pull request #2130 from pipecat-ai/aleix/pipeline-task-cancel-queue
PipelineTask: cancel idle queue before cancelling task
2025-07-03 08:32:31 -07:00
Aleix Conchillo Flaqué
af8b4901d4 DtmfAggregator: cancel interruption task to avoid a dangling task 2025-07-03 08:18:48 -07:00
Aleix Conchillo Flaqué
64c8230960 PipelineTask: cancel idle queue before cancelling task 2025-07-03 08:18:21 -07:00
Aleix Conchillo Flaqué
bf664534cc PipelineTask: cancel idle queue before cancelling task 2025-07-03 08:15:31 -07:00
Filipi da Silva Fuchter
274a04e535 Merge pull request #2129 from carolin-tavus/carolin-tavus/add-persona-validation
Add persona validation (check that microphone is enabled)
2025-07-03 11:49:42 -03:00
carolin-tavus
cb81f3d50e format 2025-07-03 14:38:20 +00:00
carolin-tavus
30a3b24287 Add persona validation (check that microphone is enabled) 2025-07-03 14:04:04 +00:00
Filipi da Silva Fuchter
8aacf71956 Merge pull request #1623 from phamtrung0633/victor/azure-tts-interruption-fix
Azure TTS fixed by clearing the audio queue before synthesizing the next text
2025-07-03 10:51:54 -03:00
Victor
72d503d3a3 Azure TTS fixed by clearing the audio queue before synthesizing the next text 2025-07-03 10:48:26 -03:00
Aleix Conchillo Flaqué
453a904290 Merge pull request #2123 from pipecat-ai/aleix/dev-requirements-25-07-02
update dev-requirements (dependabot)
2025-07-02 23:00:40 -07:00
Mark Backman
368bff4fb4 Merge pull request #2101 from pipecat-ai/mb/fix-websocket-example-dir
fix: remove javascript directory from the websocket README
2025-07-02 22:55:47 -04:00
Mark Backman
4ae045d704 Add docs deprecation for handle_function_call_start 2025-07-02 19:53:48 -07:00
Mark Backman
8c71939425 Merge pull request #2122 from pipecat-ai/mb/deprecation-docstrings
Add deprecation directives, add indexing, only autodoc members
2025-07-02 21:31:02 -04:00
Aleix Conchillo Flaqué
a437c2d365 update examples (dependabot) 2025-07-02 16:33:24 -07:00
Aleix Conchillo Flaqué
a1784e3237 update dev-requirements (dependabot) 2025-07-02 16:09:13 -07:00
Mark Backman
abee0f853c Add deprecation directives, add indexing, only autodoc members 2025-07-02 15:44:02 -07:00
Aleix Conchillo Flaqué
e9d358ed17 Merge pull request #2119 from pipecat-ai/aleix/llm-messages-append-update-run-llm
add run_llm to LLMMessagesAppendFrame and LLMMessagesUpdateFrame
2025-07-02 13:53:36 -07:00
Aleix Conchillo Flaqué
c5d54d06bb add run_llm to LLMMessagesAppendFrame and LLMMessagesUpdateFrame 2025-07-02 13:53:13 -07:00
Filipi da Silva Fuchter
c16eed7ca2 Merge pull request #2091 from pipecat-ai/filipi/sample_rate
Creating a new stream resampler which avoids clicks.
2025-07-02 16:22:46 -03:00
Filipi Fuchter
76388a10b5 Deprecating the create_default_resampler and adding the changelog. 2025-07-02 16:20:58 -03:00
Filipi Fuchter
38bcc033a2 Improving the docs about when to use: SOXRAudioResampler x SOXRStreamAudioResampler 2025-07-02 16:20:48 -03:00
Filipi Fuchter
5af563cd91 Configured the services to use create_stream_resampler instead of create_default_resampler 2025-07-02 16:20:34 -03:00
Filipi Fuchter
3de271161c Fixing the ruff script to also try to fix docstrings. 2025-07-02 16:19:57 -03:00
Filipi Fuchter
c19f9bc43a Creating a new stream resampler which avoids clicks. 2025-07-02 16:19:47 -03:00
Mark Backman
ef85d245ed Merge pull request #2120 from haayhappen/patch-1
Update README.md
2025-07-02 15:18:28 -04:00
Fynn Merlevede
25749bd4c0 Update README.md
fix: use correct protocol in READme
2025-07-02 20:57:38 +02:00
Mark Backman
e19c5464fe Merge pull request #2114 from pipecat-ai/mb/bump-google-genai-version
Upgrade google-genai version to 1.24.0
2025-07-02 14:25:29 -04:00
Mark Backman
5c2ea3b804 Upgrade google-genai version to 1.24.0 2025-07-02 11:18:37 -07:00
Aleix Conchillo Flaqué
c27348d470 Merge pull request #2118 from pipecat-ai/aleix/daily-python-0.19.4
pyproject: update daily-python to 0.19.4
2025-07-02 10:38:54 -07:00
Aleix Conchillo Flaqué
de5f9c9217 pyproject: update daily-python to 0.19.4 2025-07-02 09:51:36 -07:00
Aleix Conchillo Flaqué
f9086ee3a2 Merge pull request #2110 from pipecat-ai/aleix/daily-add-virtual-speaker-support
DailyTransport: allow receiving audio in a single track
2025-07-02 09:50:02 -07:00
Vanessa Pyne
43298a9026 Merge pull request #2077 from yousifa/mcp-http-gemini-support
Mcp http gemini support
2025-07-02 11:47:25 -05:00
Vanessa Pyne
d80e228c6f Merge branch 'main' into mcp-http-gemini-support 2025-07-02 11:47:18 -05:00
Mark Backman
2902362886 Merge pull request #2115 from pipecat-ai/mb/docstring-cleanup
Docstring cleanup, fix missing examples imports
2025-07-02 11:35:11 -04:00
Mark Backman
1cd303ad7f Merge pull request #2090 from pipecat-ai/mb/silero-np-error
Remove redundant import and global in SileroOnnxModel
2025-07-02 11:28:11 -04:00
Mark Backman
f590a476e7 Gemini Live fixes, plus additional docstrings 2025-07-02 08:27:23 -07:00
Mark Backman
e71cb3ba68 Docstring cleanup, fix missing examples imports 2025-07-02 08:27:23 -07:00
Filipi da Silva Fuchter
510a9af2e5 Merge pull request #2116 from pipecat-ai/filipi/fix_ios_chatbot_demo
Fixed an issue to disconnect the iOS chatbot demo.
2025-07-02 12:13:51 -03:00
Filipi Fuchter
5328f84df4 Fixed an issue to disconnect the iOS chatbot demo. 2025-07-02 12:06:15 -03:00
Yousif Astarabadi
18817fd81b added docstring in public GeminiFileAPI module 2025-07-02 00:09:48 -07:00