compare
Vosk vs WhisperLive
The same facts for both, read from GitHub every night, and the relation a person reviewed.
| Fact | Vosk | WhisperLive |
|---|---|---|
| Language | Jupyter Notebook | Python |
| Licence | Apache-2.0 | MIT |
| Stars | 15k | 4.3k |
| Latest | v0.3.50 | v0.10.0 |
| Last push | 2026-10-15 | 2026-10-07 |
| Release cadence | about 101 days between releases | about 87 days between releases |
| Active contributors | 2 commit authors on the default branch in the last 90 days | 6 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.
PartialWhisperLiveNear-live transcription of microphone or stream audio over WebSocket, run on your own server.
Vosk
WhisperLive
Vosk
unsigned The latest release, v0.3.50, carries no signature GitHub could verify.
Loading the security report
WhisperLive
✓ signed The latest release, v0.10.0, carries a signature GitHub verified.
Loading the security report