Skip to content
RobothecaBeta
Log in

Vosk

  • Software
  • Perception
  • Library

Vosk is an offline open source speech recognition toolkit supporting more than 20 languages, with streaming recognition and bindings for many programming languages.

Made by Alpha Cephei.

Source on GitHub: github.com/alphacep/vosk-api (opens in a new tab). Facts read at commit 4ab9821 (opens in a new tab).

Licenses

Code
Apache-2.0 (opens in a new tab)

Read by Robotheca from COPYING (opens in a new tab) (Apache-2.0) at commit 4ab9821 (opens in a new tab), on 16 Oct 2026.

Commercial use
Yes

What it does

  • Runs speech recognition fully offline.
  • Supports more than 20 languages and dialects, including English, German, French, Spanish and Chinese.
  • Small models of about 50 MB provide continuous large vocabulary transcription with zero-latency streaming.
  • Offers reconfigurable vocabulary and speaker identification.
  • Provides bindings for Python, Java, Node.JS, C#, C++, Rust, Go and others.
  • Suited to chatbots, smart home appliances, virtual assistants, movie subtitles and lecture transcription.

Written by Robotheca from the project's README (opens in a new tab) at commit 4ab9821.

Getting started

Difficulty
Intermediate
Hardware it needs, as the project states it
Scales from small devices such as a Raspberry Pi or an Android smartphone up to big clusters.

Maintenance

Status
Active: a commit in the last 90 days
Newest commit
15 Oct 2026 on master
Latest release
v0.3.50 (22 Apr 2024)

Checked on GitHub on 16 Oct 2026.

Links

Robots on Robotheca that use it

No robot on Robotheca is linked to it yet. Links come from a robot's robot.yaml, from its dependency files read as text, or from Robotheca's editors.

Robotheca lists software as a reference: nothing is hosted or run here, and every fact links to where it was read.