WhisperLiveKit

Live captions for meetings or streams mean uploading audio to the cloud, while local Whisper waits for the whole recording. WhisperLiveKit is a local, real-time streaming speech-to-text tool that transcribes as you speak and separates speakers.

It translates live and offers OpenAI- and Deepgram-compatible APIs to replace cloud services.

Features

Streaming:Text as you speak.

Diarization:Who said what.

Translation:Many languages.

Compatible APIs:OpenAI and Deepgram.