Vendor page
Vosk models (Alpha Cephei)
Alpha Cephei, 2026
Read the originalRead on October 17, 2026
- What it is
- The model list for the Vosk speech recognition API. It gives each English and other-language model's download size, word error rate on named test sets, a short note and its license.
- How much weight it carries
- Published by the Vosk maintainers, so it is their own measurement, on their chosen test sets (LibriSpeech, TED-LIUM, and others). It is not an independent benchmark, and the test sets differ from those on the Open ASR Leaderboard.
Facts taken from this source
- Vosk says its big models can require up to 16 GB of memory, because they use more advanced algorithms.
“Big models require up to 16Gb in memory since they apply advanced AI algorithms.” (Models section, first paragraph)
- Vosk says its big models have a fixed vocabulary that cannot be changed while the model runs.
“Big models are static the vocabulary can not be modified in runtime.” (Models section, first paragraph)
- Vosk's 1.8 GB English model vosk-model-en-us-0.22 had a word error rate of 5.69 percent on LibriSpeech test-clean, and it is listed under the Apache 2.0 license.
“vosk-model-en-us-0.22 1.8G 5.69 (librispeech test-clean) 6.05 (tedlium) 29.78(callcenter) Accurate generic US English model Apache 2.0” (Model list table)
- Vosk's small English model vosk-model-small-en-us-0.15, at 40 MB, had a word error rate of 9.85 percent on LibriSpeech test-clean, and it is listed under the Apache 2.0 license.
“vosk-model-small-en-us-0.15 40M 9.85 (librispeech test-clean) 10.38 (tedlium) Lightweight wideband model for Android and RPi Apache 2.0” (Model list table)
- Vosk says a small model is around 50 MB on disk and needs about 300 MB of memory while it runs.
“Small model typically is around 50Mb in size and requires about 300Mb of memory in runtime.” (Models section, first paragraph)