whatmodel.sh / stt / Vosk small en-us 0.15
Vosk small en-us 0.15
↗ share
+ contribute
Vosk small en-us 0.15 is an open-weights speech-to-text model from Alpha Cephei (Vosk), released December 2020. Licence: apache-2.0.
Catalogue identity notes
Exact Vosk (Kaldi-based) English model 'vosk-model-small-en-us-0.15' from alphacephei.com/vosk/models (listed 40M, Apache 2.0; page's own WER 9.85 (librispeech test-clean) 10.38 (tedlium)). Kaldi TDNN-style offline/streaming recogniser, the landmark pre-neural-end-to-end open ASR stack. released: not stated on the models page (left unset).
Model information sources
Score within the Open ASR English short-form WER (March 2026) comparison set only.
$ how it compares
The speech-to-text models ranked either side of Vosk small en-us 0.15, out of 176 with a score, then more from Alpha Cephei (Vosk).
| # | model | score | where | ||
|---|---|---|---|---|---|
| 156 |  Whisper base.en | 35±3 | local | ||
| 157 |  SpeechBrain wav2vec2 CTC (LibriSpeech) | 35±4 | local | ||
| 158 | Vosk small en-us 0.15 | 31±6 | local | ||
| 159 |  Moonshine Tiny | 29±3 | local | ||
| 160 | Moonshine Streaming Tiny | 28±3 | local | ||
| more from Alpha Cephei (Vosk) | |||||
| 146 | Vosk en-us 0.22 | 42±6 | local | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
other tests3 not in a task · 85% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Picovoice STT benchmark · English streaming 4-set mean WER | 18.4% ✎ | █·█···▄▄▄··▄ beats 3/7 | 67% |
| LibriSpeech test-clean WER lab | 9.8% ✎ | ▁·▃·▁▁▁▁▃▇█▆ beats 2/100 | 14% |
| TED-LIUM test WER (short-form) lab | 10.4% ✎ | ▁·▁▇█▃·▁▁▃█▄ beats 13/27 | 3.3% |
$ where to run it
Other ways to run it
- Run it as published · needs ~0.3 GB · from github.com/alphacep (official)
uvx --from vosk vosk-transcriber -n vosk-model-small-en-us-0.15 -i audio.wav -o out.txt
Weights and documentation: alphacephei.com ↗
$ how the score was worked out · Picovoice speech-to-text-benc… 67%, Alpha Cephei Vosk models page… 18%
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Picovoice speech-to-text-benchmark · English batch-engine WER (README) | 1 | 67% |
| Alpha Cephei Vosk models page (vendor-reported WER for its own Vosk models) · lab-reported | 2 | 18% |
| prior · pull toward the middle | 15% | |
| weighted average | = 30.8 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json