TiloBox
Back to directory
WhisperX project preview

WhisperX

Automatic speech recognition with word-level timestamps and speaker diarization.

LicenseBSD-2-Clause
GitHub stars15.5k
Last commit1 weeks ago
Tags6 topics
Ai MlWord TimestampsForced AlignmentPythonSpeech DiarizationPytorch
Overview

Why consider WhisperX?

WhisperX extends OpenAI Whisper with phoneme-level forced alignment (via wav2vec2) and speaker diarization (via pyannote.audio). It delivers precise word-level timestamps and speaker labelling at 70x real-time speed.

Guided learning

Learn WhisperX by building

Practical setup notes, real use cases, and copy-ready examples in one focused guide.

1 min read 2 sections
In this guide2 sections

Overview of WhisperX

WhisperX aligns Whisper transcripts with phoneme audio boundaries, enabling exact karaoke subtitling and multi-speaker podcast transcription.

Quickstart

bash
1pip install whisperx
2whisperx audio.mp3 --model large-v3 --diarize --hf_token YOUR_HF_TOKEN

WhisperX is licensed under the BSD-2-Clause License.

Related tools

More options with a similar category or technology profile.

WhisperX FAQs

WhisperX is listed as a Ai Ml tool on TiloBox. Review the overview, features, and official documentation on this page to decide whether it solves your specific workflow.

Start with the project's GitHub repository for supported installation and deployment instructions. Test the setup with representative data or a small project before rolling it out more widely.

WhisperX is listed under the BSD-2-Clause license. Read the complete license text and the project's notices before using, modifying, or distributing the software.

Production readiness depends on your requirements. Review maintenance activity, security practices, documentation, backup and upgrade procedures, and compatibility with your stack; then validate it in a non-production environment.

WhisperX is listed as an alternative to Descript. Compare the core workflow, deployment model, integrations, and licensing against your must-have requirements before switching.