agents
agents copied to clipboard
Build real-time multimodal AI applications 🤖🎙️📹
livekit.agents.tokenize._basic_paragraph.split_paragraphs ```python def split_paragraphs(text: str) -> list[tuple[str, int, int]]: """ Split the text into paragraphs. Returns a list of paragraphs with their start and end indices of the original text....
Hi, Since this is a recent repository, if someone wants to generate code that uses this library in either chatGPT or any other coding assistant it doesn't work. Would it...
Users need a way to get the transcript for both the agent and participant(s). Currently, the expectation (based on [docs](https://docs.livekit.io/agents/voice-agent/transcriptions/)) is that the developer would listen for the `transcription_received` event....
Suggestion for enhanced efficiency in setup.py code.
using the example here, the agent doesn't seem to receive any of the functions in the session configuration: https://github.com/livekit/agents/blob/main/examples/multimodal_agent.py not sure if this is an issue with the example or...
I have added support for the non streaming and non auto regressive model by [smallest.ai](https://smallest.ai), following the existing TTS structure in adjacent plugins.
Originally `speech_buffer` got only a subset of the audio data for each audio frame from mic bc of ```python to_copy_buffer = min(self._model.window_size_samples, available_space) ``` This makes the subsequent non-stream STT...
converted example table from bullets to the table
For agents using streaming STT, the VAD isn't strictly necessary. In particular this reduces CPU usage quite a bit.
This PR was opened by the [Changesets release](https://github.com/changesets/action) GitHub action. When you're ready to do a release, you can merge this and the packages will be published to npm automatically....