OpenAI Whisper
The open reference model for speech-to-text.
⬦ Free and open source
Released under the MIT license. There is no affiliate link on this page. The button goes straight to the project.
Free and open source, released under the MIT license. This page carries no affiliate link. The button goes to the official project.
Get OpenAI Whisper →Whisper is the model that made local, high-quality transcription normal. It is MIT licensed, so you can run it on your own machine with no per-minute bill and no data leaving your control.
The one caveat: plain Whisper is not fast. In practice most people run faster-whisper (a CTranslate2 reimplementation, also MIT) for a several-times speedup. Either way, this is the honest free answer to every paid transcription service.
The good
- Genuinely multilingual and robust
- MIT licensed, run it anywhere
- The baseline every other STT tool is measured against
The catch
- Vanilla Whisper is slow without optimization
- Needs a GPU for real-time on larger models
- No built-in diarization
Pricing
Free and open source. Runs locally on your own hardware.
Alternatives to consider
- Piper Fast, lightweight neural text-to-speech that runs offline.
- Kokoro-82M A tiny 82M-parameter TTS model with quality above its weight.