Commit Graph

648 Commits

Author SHA1 Message Date
padillamt
b68f044ef7 mtpadilla: updated example to reflect parameter placement changes in base Inworld TTS class 2025-07-25 15:13:43 -07:00
padillamt
8e66794759 mtpadilla: switch to Deepgram ASR for lower latency 2025-07-24 22:22:36 -07:00
padillamt
f982ace4c5 inworld: removal of unnecessary setting of ssampling rate since matches default 2025-07-24 21:56:01 -07:00
padillamt
81048ce43a mtpadilla: rename 07aa-interruptible-inworld-http.py to 07ab-interruptible-inworld-http.py 2025-07-24 20:42:29 -07:00
padillamt
da8c67114a mtpadilla: make streaming the default for example 2025-07-24 13:35:29 -07:00
padillamt
b6367965cb mtpadilla: consolidate streaming and non-streaming options into a single class with common API, with boolean switch variable added (streaming) 2025-07-23 16:50:32 -07:00
padillamt
147bf9cfe8 mtpadilla: addition of non-streaming option with own dedicated class, and related additional non-streaming test option 2025-07-23 15:28:43 -07:00
padillamt
0d5292c4ef inworld: typo fix in voice name 2025-07-21 13:48:13 -07:00
padillamt
4853d5d55c inworld: updated InworldHttpTTSService initialization 2025-07-21 13:27:25 -07:00
padillamt
4250aa6616 inworld: removal of backup copy, no longer needed 2025-07-21 10:11:50 -07:00
padillamt
5d8c184d99 inworld: commit of original text file and changes that copy openai's with Inworld TTS as only change 2025-07-18 16:30:03 -07:00
padillamt
c67b779b91 inworld: first commit of Inworld example file for TTS 2025-07-15 17:21:16 -07:00
Mark Backman
6cf254e2f9 Fix: missing import in 26f foundational example, update twilio transport_params to FastAPIWebsocketParams 2025-07-03 13:58:18 -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
Yousif
09aa168840 Merge branch 'pipecat-ai:main' into mcp-http-gemini-support 2025-07-01 23:54:42 -07:00
vipyne
f1c9f5040b Update examples/foundational/26f-gemini-multimodal-live-files-api.py 2025-07-01 16:27:25 -05:00
vipyne
79e51051c7 New lint rules and remove unused example file 2025-07-01 16:27:25 -05:00
getchannel
6e6e932370 Create 26g-gemini-multimodal-live-groundingMetadata.py 2025-07-01 16:27:25 -05:00
getchannel
7b1071b30d Create 26f-gemini-multimodal-live-files-api.py
This is an example to test usage of the Files API integration. Specifically with the Gemini Multimodal Live Service.
2025-07-01 16:27:25 -05:00
Mark Backman
324546b4e7 Merge pull request #2098 from StrongMind/aws-session-token
Add support for session token in AWS Nova Sonic service
2025-07-01 16:25:38 -04:00
kompfner
de74284a8e Merge pull request #2051 from pipecat-ai/pk/direct-functions
Implement "direct functions", which allow you to bypass specifying a …
2025-07-01 14:19:33 -04:00
Paul Shippy
f891140a74 Update sample to take in session token 2025-06-30 17:35:50 -07:00
Kwindla Hultman Kramer
55cfea776f Merge branch 'main' into khk/gemini-thinking-default 2025-06-30 10:32:42 -07:00
Paul Kompfner
a3e540eb32 Rename examples/foundational/14s-function-calling-direct.py to examples/foundational/14t-function-calling-direct.py, since a new "14s" example was added 2025-06-30 10:44:55 -04:00
Paul Kompfner
e01c20be84 Remove unused import and tweak a comment 2025-06-30 10:36:47 -04:00
Paul Kompfner
15b9a5faf6 Implement "direct functions", which allow you to bypass specifying a function configuration (as a FunctionSchema or in a provider-specific format) and use the Python function directly. Metadata is gathered automatically from the function signature and docstring. 2025-06-30 10:36:42 -04:00
Kwindla Hultman Kramer
3afa30894f Turn off thinking for Gemini models by default 2025-06-28 12:23:35 -07:00
Yousif Astarabadi
cafbda1668 remove openai from mcp run http example 2025-06-26 20:21:07 -07:00
Yousif Astarabadi
0c20668008 fixed linter errors 2025-06-26 20:08:26 -07:00
Yousif Astarabadi
92df8dc43c fix formatting 2025-06-26 20:08:23 -07:00
Yousif Astarabadi
9d5f5844b8 clean mcp schema for gemini models, update http mcp example to use gemini 2025-06-26 20:07:54 -07:00
Mark Backman
2cf31884d0 fix: example 42 incorrect import 2025-06-26 21:52:14 -04:00
vipyne
37929533af mcp_service: lint 2025-06-26 15:00:20 -05:00
Mark Backman
f0bcc9d9ba Add MCPClient docstrings. Removed google specific cleanup, changed example to openai 2025-06-26 12:29:45 -07:00
Yousif Astarabadi
1cac028bfe example using http transport for mcp client 2025-06-26 12:16:35 -07:00
Jorge Piedrahita Ortiz
851cf079c3 Merge branch 'main' into snova-jorgep/sambanova-integration 2025-06-24 16:00:28 -05:00
jhpiedrahitao
dfb0da32a9 fmt 2025-06-24 15:59:40 -05:00
Aleix Conchillo Flaqué
f450da57e5 Merge pull request #2056 from pipecat-ai/khk/fix-22d
Update google libraries used in google audio-in examples
2025-06-24 13:47:59 -07:00
vipyne
20047c369e mcp: update examples to use SseServerParameter 2025-06-24 12:58:39 -05:00
Kwindla Hultman Kramer
7a48316534 update google libraries used in google audio-in examples 2025-06-24 09:52:04 -07:00
Mark Backman
f52ac6e99c Merge pull request #1998 from pipecat-ai/mb/fix-38-smart-turn-fal 2025-06-23 17:15:29 -04:00
jhpiedrahitao
a51280afa6 add 13 and 14 type foundational examples for sambanova iontegration 2025-06-23 12:53:32 -05:00
Mark Backman
9146def21b Update examples to use default allow_interruptions, fixes to align examples 2025-06-19 10:07:32 -04:00
Mark Backman
c94c51d44f Fix: 38-smart-turn-fal 2025-06-17 15:10:52 -04:00
Mark Backman
22f4f0b79e Update 14e example name 2025-06-12 11:45:59 -04:00
Aleix Conchillo Flaqué
03eb22fe0a examples(22b): remove unnecessary parallel pipeline branch 2025-06-10 09:05:58 -07:00
Shrey Gupta
96fa62fdfe [Add] Support for Cartesia AI STT (#1982) 2025-06-09 14:51:01 -03:00
Brian Mathiyakom
10bd969636 Remove instantiation of unused http client session
These examples don't make any HTTP requests with `session` so there
doesn't seem be a need to create one in the first place. Probably a
copy-paste from a previous example.
2025-06-05 11:45:13 -07:00
Aleix Conchillo Flaqué
ab4b48c823 examples(04a): fix daily_runner import 2025-06-02 12:01:26 -07:00
Mark Backman
ab18b280e9 Merge pull request #1943 from pipecat-ai/mb/add-transcription-19-openai
Add a TranscriptProcessor to 19-openai-realtime-beta.py
2025-06-02 13:01:52 -04:00