FreeAIRepo
Voice & audio

m-bain/whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

BSD-2-Clause8 GB VRAMPython
Stars
25k
Forks
2.5k
Open issues
178
Last push
3d ago

About whisperX

whisperX is a free, open-source AI voice and audio tool by m-bain, written mainly in Python. WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization). It has 25k GitHub stars and 2.5k forks, and was last updated 3d ago. It's released under the BSD-2-Clause license, a standard open-source license. According to its README, it needs a GPU with at least 8 GB of memory.

License
BSD-2-Clause
Language
Python
Stars
24,772
Last update
3d ago
Runs on Mac
Not stated
GPU
8 GB+ (per README)
Paid API key
Not stated
Self-hostable
Not stated

Similar free tools

All Voice & audio tools →

whisperX FAQ

Is whisperX free?

Yes. whisperX is open source and free to use. It's released under the BSD-2-Clause license, a standard open-source license.

Does whisperX run on a Mac?

Its README doesn't say. Check the installation guide on GitHub before you start.

Does whisperX need a GPU?

According to its README, whisperX needs a GPU with at least 8 GB of memory.

Is whisperX still maintained?

Yes. It was last updated 3d ago and has 178 open issues on GitHub.

What are alternatives to whisperX?

Similar free, open-source tools include Speech, whisper.cpp, FunASR, whisper.

Related topics