
Meetings & transcription
WhisperLive
Near-live transcription of a microphone or an audio file
★ 4.2k
August 2026
MIT
Meetings & transcription
What it does
Transcribes speech as it happens rather than after the fact, and also handles pre-recorded files. It supports word-level timestamps, custom vocabulary for names and jargon, and speaker diarization. The design splits into a server and a client, which you start separately - so setup is developer-oriented and needs Python or Docker. If you only want to transcribe a finished recording, a simpler tool will suit you better.
Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.
Screenshots & visuals


Before you start
- Setup difficultySome setup needed
- Command lineRequired
- API keyRequired
- Sends data onlineYes
Judged automatically from the project's own metadata. Always confirm on the official page.
WhisperLive FAQ
- Is WhisperLive free?
- WhisperLive itself is free, but it needs an API key for an external AI service. That service charges separately, though some have a free tier.
- Do I need to install anything or write code to use WhisperLive?
- It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.
- Does WhisperLive work on a phone?
- No. It needs a computer.
- Can I use WhisperLive commercially?
- The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.