pipecat/CHANGELOG.md

Changelog

All notable changes to pipecat will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[Unreleased]

Added

• Added initial interruptions support.

• Added VADParams so you can control voice confidence level and others.

Fixed

• Fixed issues with Ctrl-C program termination.

[0.0.16] - 2024-05-16

Fixed

• DailyTransport: don't publish camera and audio tracks if not enabled.

• Fixed an issue in BaseInputTransport that was causing frames pushed downstream not pushed in the right order.

[0.0.15] - 2024-05-15

Fixed

• Quick hot fix for receiving DailyTransportMessage.

[0.0.14] - 2024-05-15

Added

• Added DailyTransport event on_participant_left.

• Added support for receiving DailyTransportMessage.

Fixed

• Images are now resized to the size of the output camera. This was causing images not being displayed.

• Fixed an issue in DailyTransport that would not allow the input processor to shutdown if no participant ever joined the room.

• Fixed base transports start and stop. In some situation processors would halt or not shutdown properly.

[0.0.13] - 2024-05-14

Changed

• MoondreamService argument model_id is now model.

• VADAnalyzer arguments have been renamed for more clarity.

Fixed

• Fixed an issue with DailyInputTransport and DailyOutputTransport that could cause some threads to not start properly.

• Fixed STTService. Add max_silence_secs and max_buffer_secs to handle better what's being passed to the STT service. Also add exponential smoothing to the RMS.

• Fixed WhisperSTTService. Add no_speech_prob to avoid garbage output text.

[0.0.12] - 2024-05-14

Added

• Added DailyTranscriptionSettings to be able to specify transcription settings much easier (e.g. language).

Other

• Updated simple-chatbot with Spanish.

• Add missing dependencies in some of the examples.

[0.0.11] - 2024-05-13

Added

• Allow stopping pipeline tasks with new StopTaskFrame.

Changed

• TTS, STT and image generation service now use AsyncGenerator.

Fixed

• DailyTransport: allow registering for participant transcriptions even if input transport is not initialized yet.

Other

• Updated storytelling-chatbot.

[0.0.10] - 2024-05-13

Added

• Added Intel GPU support to MoondreamService.

• Added support for sending transport messages (e.g. to communicate with an app at the other end of the transport).

• Added FrameProcessor.push_error() to easily send an ErrorFrame upstream.

Fixed

• Fixed Azure services (TTS and image generation).

Other

• Updated simple-chatbot, moondream-chatbot and translation-chatbot examples.

[0.0.9] - 2024-05-12

Changed

Many things have changed in this version. Many of the main ideas such as frames, processors, services and transports are still there but some things have changed a bit.

• Frames describe the basic units for processing. For example, text, image or audio frames. Or control frames to indicate a user has started or stopped speaking.

• FrameProcessors process frames (e.g. they convert a TextFrame to an ImageRawFrame) and push new frames downstream or upstream to their linked peers.

• FrameProcessors can be linked together. The easiest wait is to use the Pipeline which is a container for processors. Linking processors allow frames to travel upstream or downstream easily.

• Transports are a way to send or receive frames. There can be local transports (e.g. local audio or native apps), network transports (e.g. websocket) or service transports (e.g. https://daily.co).

• Pipelines are just a processor container for other processors.

• A PipelineTask know how to run a pipeline.

• A PipelineRunner can run one or more tasks and it is also used, for example, to capture Ctrl-C from the user.

[0.0.8] - 2024-04-11

Added

• Added FireworksLLMService.

• Added InterimTranscriptionFrame and enable interim results in DailyTransport transcriptions.

Changed

• FalImageGenService now uses new fal_client package.

Fixed

• FalImageGenService: use asyncio.to_thread to not block main loop when generating images.

• Allow TranscriptionFrame after an end frame (transcriptions can be delayed and received after UserStoppedSpeakingFrame).

[0.0.7] - 2024-04-10

Added

• Add use_cpu argument to MoondreamService.

[0.0.6] - 2024-04-10

Added

• Added FalImageGenService.InputParams.

• Added URLImageFrame and UserImageFrame.

• Added UserImageRequestFrame and allow requesting an image from a participant.

• Added base VisionService and MoondreamService

Changed

• Don't pass image_size to ImageGenService, images should have their own size.

• ImageFrame now receives a tuple(width,height) to specify the size.

• on_first_other_participant_joined now gets a participant argument.

Fixed

• Check if camera, speaker and microphone are enabled before writing to them.

Performance

• DailyTransport only subscribe to desired participant video track.

[0.0.5] - 2024-04-06

Changed

• Use camera_bitrate and camera_framerate.

• Increase camera_framerate to 30 by default.

Fixed

• Fixed LocalTransport.read_audio_frames.

[0.0.4] - 2024-04-04

Added

• Added project optional dependencies [silero,openai,...].

Changed

• Moved thransports to its own directory.

• Use OPENAI_API_KEY instead of OPENAI_CHATGPT_API_KEY.

Fixed

• Don't write to microphone/speaker if not enabled.

Other

• Added live translation example.

• Fix foundational examples.

[0.0.3] - 2024-03-13

Other

• Added storybot and chatbot examples.

[0.0.2] - 2024-03-12

Initial public release.