compare
Vosk vs WhisperX
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | Vosk | WhisperX |
|---|---|---|
| Language | Jupyter Notebook | Python |
| Licence | Apache-2.0 | BSD-2-Clause |
| Stars | 15k | 25k |
| Latest | v0.3.50 | v3.8.6 |
| Last push | 2026-10-15 | 2026-10-18 |
| Release cadence | about 101 days between releases | about 7 days between releases |
| Active contributors | 2 commit authors on the default branch in the last 90 days | 3 commit authors on the default branch in the last 90 days |
| Flags | none | none |
How they relate
Both replace Amazon Transcribe. Alternatives to Amazon Transcribe →
PartialVoskOffline speech recognition on your own device, without speaker labels or a managed service.
PartialWhisperXBatch transcription with speaker labels on your own hardware; no managed service or streaming.
Both replace Whisper. Alternatives to Whisper →
PartialVoskSmall offline models with streaming recognition and an API for many languages, less accurate than Whisper.
Full replacementWhisperXAdds word-level timestamps, voice activity detection and speaker diarization on top of faster-whisper.
Vosk
WhisperX
- 3.8.7rc12026-06-26Fix Windows CUDA detection: include AMD64 in uv source platform markerspre-release
- v3.8.62026-05-25Add Indonesian model to alignment.py
- v3.8.52026-04-01fix: pin torchvision and torchcodec for torch 2.8 compatibility
- v3.7.92026-03-25Backport of word-level timestamp fixes from v3.8.4.
- v3.5.22026-03-25Backport of word-level timestamp fixes from v3.8.4.
Vosk
unsigned The latest release, v0.3.50, carries no signature GitHub could verify.
Loading the security report
WhisperX
unsigned The latest release, v3.8.6, carries no signature GitHub could verify.
Loading the security report