WhisperX
Whisper with word-level timestamps and speaker diarization
About
WhisperX is a Whisper-based automatic speech recognition pipeline that adds word-level timestamps via forced phoneme alignment and uses voice-activity detection to batch audio for fast inference (around 70x realtime with the large-v2 model). It supports speaker diarization through external models and runs on GPU with CUDA 12.8 or on CPU. Useful for subtitles, transcript editing, and meeting-style audio where word offsets matter.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Audio & Speech
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Intermediate (3/5)
- License
- BSD-4-Clause
- Added
- Jan 29, 2026
Related Tools
Free text-to-speech generator with multiple voices, accents, and languages. No signup required.
CTranslate2-based Whisper with 4x faster transcription
Universal neural vocoder from NVIDIA that converts mel spectrograms into waveforms up to 44 kHz.
End-to-end Chinese and English spoken dialogue model from Zhipu AI with streaming speech output.
Audio foundation model unifying speech recognition, understanding, and conversation in one 7B model.
Deep learning toolkit for text-to-speech synthesis
Mentioned in
Beyond Whisper: Parakeet, SenseVoice and ASR in 2026
Whisper is no longer the default: how Parakeet, SenseVoice, Kimi-Audio, Ultravox and Moshi compare on...
Max P
whisper.cpp vs faster-whisper: Speed and Accuracy Compared
Two leading open source paths to running OpenAI Whisper. One is a CPU-friendly C/C++ port, the other rides...
Billy C