Official documentation

Vosk Offline Speech Recognition API (Alpha Cephei)

Alpha Cephei, 2026

Read on October 17, 2026

What it is: The home page of Vosk, an open-source offline speech recognition toolkit from Alpha Cephei. It describes the toolkit, its platforms and its per-language model sizes.
How much weight it carries: Written by the project itself, so it describes its own product. The page is undated and gives no accuracy figures, so it supports size and platform claims only.

Facts taken from this source

The Vosk project says it supports more than 20 languages and dialects, with English, Indian English, German and French among them.
“Vosk is a speech recognition toolkit. The best things in Vosk are: Supports 20+ languages and dialects” (Introduction, first list)
Alpha Cephei says Vosk's per-language models are about 50 MB each, and that much bigger server models are also available.
“Portable per-language models are only 50Mb each, but there are much bigger server models available.” (Home page, introduction)
The Vosk project says it provides a streaming API for the best user experience.
“Provides streaming API for the best user experience” (Homepage, list of main features)
The Vosk project says it allows quick reconfiguration of the vocabulary for best accuracy.
“Allows quick reconfiguration of vocabulary for best accuracy” (Homepage, list of main features)
The Vosk project says it works offline even on lightweight devices such as the Raspberry Pi, Android and iOS.
“Works offline, even on lightweight devices - Raspberry Pi, Android, iOS” (Introduction, list of strengths)

Official documentation

Alpha Cephei, 2026

Read on October 17, 2026

What it is: The home page of Vosk, an open-source offline speech recognition toolkit from Alpha Cephei. It describes the toolkit, its platforms and its per-language model sizes.
How much weight it carries: Written by the project itself, so it describes its own product. The page is undated and gives no accuracy figures, so it supports size and platform claims only.

The Vosk project says it supports more than 20 languages and dialects, with English, Indian English, German and French among them.
“Vosk is a speech recognition toolkit. The best things in Vosk are: Supports 20+ languages and dialects” (Introduction, first list)
Alpha Cephei says Vosk's per-language models are about 50 MB each, and that much bigger server models are also available.
“Portable per-language models are only 50Mb each, but there are much bigger server models available.” (Home page, introduction)
The Vosk project says it provides a streaming API for the best user experience.
“Provides streaming API for the best user experience” (Homepage, list of main features)
The Vosk project says it allows quick reconfiguration of the vocabulary for best accuracy.
“Allows quick reconfiguration of vocabulary for best accuracy” (Homepage, list of main features)
The Vosk project says it works offline even on lightweight devices such as the Raspberry Pi, Android and iOS.
“Works offline, even on lightweight devices - Raspberry Pi, Android, iOS” (Introduction, list of strengths)