Commit Graph

3308 Commits

Author SHA1 Message Date
Filipi da Silva Fuchter
b89f2611f7 Merge pull request #1539 from pipecat-ai/small_wbertc_mute_state
SmallWebRTC mute state
2025-04-10 11:26:53 -03:00
Filipi Fuchter
db0f783c55 Updating the video-transform demo to use the latest version of the SmallWebRTCTransport. 2025-04-10 11:23:28 -03:00
Filipi Fuchter
20ec323647 Refactoring the video-transform demo to be able to enable or disable the cam. 2025-04-10 11:23:05 -03:00
Filipi Fuchter
f71c09a4fd Added support in SmallWebRTCTransport to detect when remote tracks are muted. 2025-04-10 11:22:37 -03:00
Mark Backman
cba4ebfcf9 Merge pull request #1555 from pipecat-ai/mb/gemini-beta-base 2025-04-10 09:01:16 -04:00
Mark Backman
3b9a8946f9 Update GeminiMultimodalLiveLLMService base_url 2025-04-10 08:17:52 -04:00
Mark Backman
db3620c4be Merge pull request #1553 from balaji-atoa/main
feat: change default model name on live api
2025-04-10 08:10:35 -04:00
Mark Backman
11338ea92d Merge pull request #1552 from pipecat-ai/mb/p2p-capture-image
Add image capture to SmallWebRTCTransport
2025-04-10 07:52:13 -04:00
Filipi da Silva Fuchter
90563a4091 Merge pull request #1542 from pipecat-ai/small_webrtc_prebuilt_ui
Using the small-webrtc-prebuilt-ui
2025-04-10 07:39:26 -03:00
Filipi da Silva Fuchter
937f5f7cb7 Update examples/p2p-webrtc/video-transform/server/requirements.txt
Co-authored-by: Mark Backman <mark@daily.co>
2025-04-10 07:37:23 -03:00
Filipi da Silva Fuchter
4f221b817a Update examples/p2p-webrtc/video-transform/README.md
Co-authored-by: Mark Backman <mark@daily.co>
2025-04-10 07:37:07 -03:00
balaji-atoa
c79c1f65fc feat: change default model name on live api 2025-04-10 11:59:11 +05:30
Mark Backman
8ad2ad0e59 Add image capture to SmallWebRTCTransport 2025-04-09 23:01:06 -04:00
Filipi Fuchter
05b6a5ae4b Improving the video-transform readme 2025-04-09 15:55:13 -03:00
Filipi Fuchter
65fcea28ce Using the small-webrtc-prebuilt-ui 2025-04-09 15:45:30 -03:00
Kwindla Hultman Kramer
005c0b55b6 Merge pull request #1545 from pipecat-ai/khk/gem-live-0408
Gemini Multimodal Live API base_url format fix
2025-04-08 21:46:30 -07:00
Kwindla Hultman Kramer
1828127f41 small fix to wss base_url 2025-04-08 20:22:26 -07:00
Filipi da Silva Fuchter
77ab841cab Merge pull request #1532 from pipecat-ai/p2p_ios_demo
iOS demo for the p2p-webrtc video-transform example
2025-04-07 16:58:06 -03:00
Filipi Fuchter
3bbc75110a Mentioning the iOS client inside the changelog and fixing the readme. 2025-04-07 16:54:26 -03:00
Filipi Fuchter
b2ce1d9378 Merge branch 'main' into p2p_ios_demo 2025-04-07 16:50:58 -03:00
Filipi Fuchter
58714865df Using the public version of pipecat-client-ios-small-webrtc 2025-04-07 16:48:18 -03:00
Mark Backman
03b3635b0a Merge pull request #1521 from pipecat-ai/mb/increase-bot-vad-stop-secs
Increase BOT_VAD_STOP_SECS for services with slower speech patterns
2025-04-07 14:44:31 -04:00
Mark Backman
aaa7b5e626 Merge pull request #1524 from pipecat-ai/mb/tts-generate-with-text
TTS: Skip generation when there is no text
2025-04-07 14:44:18 -04:00
Varun Singh
0b8486ce39 Merge pull request #1418 from pipecat-ai/vr000m-pcc-dialin-webhook-server
Pipecat Cloud: Companion server to handle webhooks for pinless dial-in
2025-04-07 09:00:38 -07:00
Mark Backman
d4ae091ddd Update port in FastAPI README, add run steps to nextjs README 2025-04-07 11:09:43 -04:00
Mark Backman
9e0a57a6de Rename directories 2025-04-07 10:44:41 -04:00
Mark Backman
fc4c1e4110 README updates 2025-04-07 10:33:18 -04:00
Mark Backman
9b740d9e72 Merge pull request #1537 from pipecat-ai/mb/azure-tts-lang
Fix: Set language for Azure TTS services
2025-04-07 09:46:08 -04:00
Mark Backman
b03563765f Fix: Set language for Azure TTS services 2025-04-07 09:24:31 -04:00
Filipi Fuchter
a1578bd67a iOS demo for the p2p-webrtc video-transform example 2025-04-04 16:40:52 -03:00
Filipi da Silva Fuchter
6466573b84 Merge pull request #1498 from pipecat-ai/aiortc_example_ios
Improvements for the SmallWebRTCTransport
2025-04-04 16:39:06 -03:00
Filipi Fuchter
b42dc83696 Improvements for the SmallWebRTCTransport:
- Wait until the pipeline is ready before triggering the `connected` event.
  - Queue messages if the data channel is not ready.
  - Update the aiortc dependency to fix an issue where the 'video/rtx' MIME type
    was incorrectly handled as a codec retransmission.
  - Avoid initial video delays.
2025-04-04 16:33:57 -03:00
Filipi Fuchter
fe5931b884 Updating aiortc to fix an issue where 'video/rtx' MIMEType retransmission incorrectly handled as a codec 2025-04-04 16:28:54 -03:00
Filipi Fuchter
4b438ff7d7 Allowing ngrok connections to the video-transform demo 2025-04-04 16:28:37 -03:00
Filipi da Silva Fuchter
89a8c16676 Merge pull request #1531 from pipecat-ai/fix_chunk_default_value
Fixed SmallWebRTCTransport to support dynamic chunk values.
2025-04-04 16:04:05 -03:00
Filipi Fuchter
c4c92585f9 Fixed SmallWebRTCTransport to support dynamic chunk values. 2025-04-04 15:38:12 -03:00
Mark Backman
63146d6f85 TTS: Skip generation when there is no text 2025-04-03 16:15:58 -04:00
Mattie Ruth
ec00edc893 Update client examples to use latest versions (#1523) 2025-04-03 15:47:03 -04:00
Mark Backman
a21be058e2 Increase BOT_VAD_STOP_SECS for services with slower speech patterns 2025-04-03 15:25:48 -04:00
Mark Backman
c226c20e12 Merge pull request #1519 from pipecat-ai/mb/ref-docs-toc
Docs: Update ToC With Adapters and Observers
2025-04-03 15:19:35 -04:00
Aleix Conchillo Flaqué
78e6669105 Merge pull request #1514 from pipecat-ai/aleix/producer-consumer-processors
processors: add ProducerProcessor and ConsumerProcessor
2025-04-03 12:18:49 -07:00
Aleix Conchillo Flaqué
79f29e14dd processors: add ProducerProcessor and ConsumerProcessor 2025-04-03 09:44:56 -07:00
Mark Backman
d4a00fd080 Merge pull request #1517 from pipecat-ai/mb/update-simple-chatbot-packages
Update client packages for simple-chatbot JS and React
2025-04-03 10:07:40 -04:00
Mark Backman
d4186fa115 Merge pull request #1518 from pipecat-ai/mb/openai-verse
Add verse voice and bump the OpenAI version
2025-04-03 09:48:09 -04:00
Mark Backman
3536cbcd13 Add docstrings to FunctionSchema, update CONTRIBUTING.md with docstrings guidance, ignore __init__ docstrings if a class is sufficiently documented 2025-04-03 09:21:26 -04:00
Mark Backman
e3bcb70b13 Update ToC With Adapters and Observers 2025-04-03 09:02:09 -04:00
Mark Backman
19a82f9522 Add verse voice and bump the OpenAI version 2025-04-03 08:23:59 -04:00
Mark Backman
8c0a847449 Update client packages for simple-chatbot JS and React 2025-04-03 07:43:25 -04:00
Dominic Stewart
e3704cd1a1 Updated imports to work with pipecat 0.62 (#1515) 2025-04-03 15:07:02 +08:00
Dominic Stewart
1ba037865b Call Transfer demo (#1348)
* Updated code to dial out to an operator, keep track of operator conversation while escalated and then return to conversation when finished

* Removed unnecessary imports

* Updated bot runner code, added call routing file and then updated the call transfer and voicemail detection examples

* Updated the bot files

* Made prompt one level higher in the body and an array

* Updated call transfer examples to work correctly

* Updated gemini voicemail detection example to work

* Added twilio bot support back to the bot_runner

* Moved some state management, participant management and other logic to the helper file.

* Updated comments

* Updated env and requirements file

* Ran the examples and made sure code works. Still need to work on the prompts a bit

* Fixed format issue

* Add support to disable summary in call transfer

* Added support for operator transfer mode

* Updated readme file

* Updated readme based on feedback, and handling of various properties in the json to be more flexible for future examples

* Updated number of endpoints

* Updated readme to remove fly deployment text and replaced with Pipecat Cloud

* Starting to tweak function calls and prompts

* Updated examples to more consistently call the functions and say what they need to say

* Updated examples

* Updated examples

* Updated examples to work correctly

* Add simple bot versions of dialin and dialout

* Refactored the bot runner file to make adding future examples easier

* Based on feedback, removed examples for multiple LLMs and also adjusted voicemail detection code to be simpler

* Made sure to only capture the users transcription once

* Updated readme with latest changes

* Forgot to update the order of examples in one place

* Fixed formatting issue

* Adjusted based on james feedback

* Changed default_mode to default_calltransfer_mode
2025-04-03 09:03:23 +09:00