Whisper
Whisper is a speech recognition model that turns spoken audio into text, and can also translate speech or identify the spoken language. It is aimed at developers and people who run it through the command line or Python.
Description written from the project's own page; checked by AI.
Listed in1
The jobs it does, and the closed apps it replaces
Transcription
Replaces partlyInstead of Otter.ai, Rev · For developers
What's missing
Things people miss in Whisper. Upvote what matters to you; it helps its team decide.
Facts
LicenseMIT
Runs onWindows
KindFor developers
Stars on GitHub111k
Hosted onGitHub
ActivityChanged within the last year
Something wrong?
Wrong devices, a wrong description, or it isn't really open source? A mod reviews every suggestion.
What we couldn't confirm2
- Whether the model's training data licensing or usage restrictions affect commercial use beyond the MIT code license.
- Whether any hosted or human-verified transcription service exists beyond the open-source package.