Whisper
Accurate speech-to-text in many languages, free to run on your own computer.
What it does
- Turns an audio recording into written text.
- Works with many languages and can tell which one is spoken.
- Translates speech into English with the multilingual models.
- Runs on your own computer with open source code under the MIT licence.
- Is also sold per minute through the OpenAI API.
Best for
- Transcripts of meetings, podcasts and videos.
- Developers who add speech-to-text to their own app.
- Teams who want private transcripts on their own machine.
Pricing
Free. The open source model is free to run. OpenAI's API charges US$0.006 per minute of audio for the hosted version.