Find tools › Open-source projects › Meetings & notes

faster-whisper

Open-source project · by SYSTRAN

A faster, lighter version of OpenAI's Whisper that turns speech recordings into text on your computer.

For developersPopular19,829,714 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Transcribe hours of recordings quickly on your own machine
  • Add speech-to-text to your own app
  • Create timestamped subtitles for videos

How to start

  1. Install Python on your computer.

  2. In a terminal, run pip install faster-whisper.

  3. Write a short Python script that loads a model and transcribes your audio file.

  4. For GPU speed, install the matching CUDA and cuDNN versions listed in the README.

Good to know. Requires specific matching versions of CUDA and cuDNN libraries for GPU acceleration.

Before you install

  • Checked by a personWe read what it does before listing it.
  • License: MITYou are allowed to use it under these terms.
  • Last updated 2026-11-12

More detail

A reimplementation of OpenAI's Whisper model using CTranslate2 for faster speech recognition and lower memory usage.

It speeds up transcription significantly and reduces VRAM/RAM consumption compared to the official Whisper implementation, making it ideal for processing audio files quickly.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map