Pipecat-ai

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`).

Added

- Add `use_cpu` argument to `MoondreamService`.

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.

Changed

- Use `camera_bitrate` and `camera_framerate`.

- Increase `camera_framerate` to 30 by default.

Fixed

- Fixed `LocalTransport.read_audio_frames`.

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.

Other

- Added `storybot` and `chatbot` examples.