WhisperX m-bain/whisperX

Fast batched Whisper transcription with word-level timestamps via wav2vec2 alignment and pyannote speaker diarization.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

WhisperX at a glance

Checked 15 Oct 2026

WhisperX wraps a faster-whisper backend with batched inference (README: 70x realtime with large-v2), wav2vec2 forced alignment for word timestamps, and pyannote speaker diarization. Code is BSD-2-Clause. Diarization uses the gated pyannote speaker-diarization-community-1 model (CC-BY-4.0) and needs a free Hugging Face token. README states under 8 GB GPU memory for large-v2; CPU mode is supported.

Cite this pageRepoQuarry. “WhisperX.” Checked 15 Oct 2026. https://repoquarry.dev/projects/whisperx

How much of ElevenLabs does it replace?

1 of 4 jobs. Local transcription with word timestamps and speaker labels; README notes diarization is far from perfect.

Speech generation Not covered

Voice cloning Not covered

Speech recognition Full replacement

Voice agents Not covered

For speech generation, voice cloning, voice agents, see other ElevenLabs alternatives. You may also need to build an interface, an API server and hosting yourself.

How much of Otter.ai does it replace?

2 of 3 jobs. Transcripts with generic speaker labels from recordings; no live meeting capture, names or summaries.

Meeting transcription Partial replacement

Speaker identification Partial replacement

Meeting summaries Not covered

For meeting summaries, see other Otter.ai alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction

QuestionAnswerSourceChecked

Runs on my machine? Yes, CLI and Python package on GPU or CPU This repository provides fast automatic speech recognition (70x realtime with large-v2) with word-level timestamps and speaker diarization. github.com · whisperX#readme ↗ 1d ago

Code licence BSD-2-Clause github.com · LICENSE ↗ 1d ago

Model weights licence Mixed: Whisper weights via faster-whisper (Systran conversions tagged MIT); diarization model pyannote/speaker-diarization-community-1 is CC-BY-4.0 and gated; language-specific alignment model licences are not stated in the README Speaker diarization powered by the speaker-diarization-community-1 model, licensed under CC-BY-4.0 by pyannoteAI github.com · whisperX#acknowledgements ↗ 1d ago

Commercial use BSD-2-Clause code and MIT Whisper weights allow it; diarization adds CC-BY-4.0 attribution terms, and alignment model licences vary by language and are not stated github.com · whisperX#acknowledgements ↗ 1d ago

Paid services needed? None required; diarization needs a free Hugging Face read token and accepting the pyannote model's user agreement To enable Speaker Diarization, include your Hugging Face access token (read) that you can generate from Here after the --hf_token argument and accept the user agreement for the speaker-diarization-community-1 model. github.com · whisperX#speaker-diarization ↗ 1d ago

Hardware Under 8 GB GPU memory for large-v2 with beam_size=5; CPU mode supported (int8); CUDA toolkit 12.8 for GPU faster-whisper backend, requires <8GB gpu memory for large-v2 with beam_size=5 github.com · whisperX#readme ↗ 1d ago

Operating systems Linux and Windows CUDA setup documented; macOS via CPU mode To run on CPU instead of GPU (and for running on Mac OS X) github.com · whisperX#setup ↗ 1d ago

Setup effort Medium; pip install whisperx, plus CUDA toolkit 12.8 for GPU and a Hugging Face token for diarization; ffmpeg may be needed To use WhisperX with GPU acceleration, install the CUDA toolkit 12.8 before WhisperX. Skip this step if using only the CPU. github.com · whisperX#setup ↗ 1d ago