Vosk
Fewer than 5 people recommend it so far, so there's no written verdict. Here is what commenters said.
3recommend
0warn against
Nov 14, 2025first mention
Oct 14, 2026latest mention
Why people recommend it
“I went with Vosk because it's pretty trivial to lock input down to a set vocabulary”
Show 1 more
“We also provide a websocket server and grpc server which can be used in telephony and other applications.”
Caveats and dissent
No one in these comments warned against it.
Often compared with
From the makers not counted in the ranking
this is such a poor model, I've tried it before. Try yapsnap it has better word error rate and runs super fast on CPU. https://github.com/kouhxp/yapsnap/
Threads where it came up
- Show HN: How random are you? 2 mentions
- Show HN: GeoRadios – Spin a globe, hear what's on the radio there 1 mention
- Whistle: Speech to Text in 16.9 MB 1 mention
- Agent Voice, communicate with your coding agent all from Voice, on the fly 1 mention
- Ask HN: What's the best realtime, local, TTS solution? Live call interpretation 1 mention
- Ask HN: What's the current best local/open speech-to-speech setup? 1 mention
Data: vosk.json. Quotes are verbatim; the verdict and theme labels are written by a model from these comments, and every clause links to its sources.
All comments 8
“I went with Vosk because it's pretty trivial to lock input down to a set vocabulary”
“hooked it up to vosk”
“If you need speech2text try this,”
“it uses a browser loaded, very lightweight vosk model”
“We also provide a websocket server and grpc server which can be used in telephony and other applications.”
“I've been looking into whisper and vosk in the last few days.”
“transcription using Vosk”
“Whisper does much better than stuff I've tried in the past like Vosk.”