Whisper

An open-source speech recognition model from OpenAI for transcribing and translating audio on your own machine.

These buttons open the developer's own site, repository or store listing in a new tab. wares.gg does not host downloads.

About Whisper

Whisper is a general-purpose speech recognition model trained on a large and varied audio dataset. It is multitask: besides transcribing speech in many languages, it can translate speech into English and identify which language is being spoken.

It is distributed as a Python package with a command-line tool, so audio files can be transcribed locally without sending them to a server. It suits developers, researchers and technically comfortable users who want private transcription, and it underpins many other transcription apps.

Strengths

  • Runs locally, so audio never leaves your machine
  • Transcription, translation to English and language identification
  • Supports many languages
  • Widely used, with a large community

Limitations

  • Command-line and Python setup, no graphical interface
  • Larger models are slow without a capable GPU

Details

Pricing
FreeFree and open source, including the model weights.
License
MIT
Developer
OpenAI
Platforms
Windows, macOS, Linux, Command line
How it runs
Downloadable app
Account
Not required
Works offline
Yes
Best suited for
Private, local transcription of recordings by technical users
Last verified
Added
Provenance
Selected from the TechWalrus Resource Hub (AI); facts checked against the developer's own pages, 2 sources on file.

Report a wrong fact or a dead link on this listing