# Vosk

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

Repository: https://github.com/alphacep/vosk-api
Canonical: https://ross.abutalabs.com/products/vosk
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Topics: speech-recognition, asr, voice-recognition, speech-to-text, android, ios, raspberry-pi, deep-learning, deep-neural-networks, speech-to-text-android, speaker-identification, speaker-verification, python, offline, privacy, kaldi, deepspeech, google-speech-to-text, vosk, stt
Last push: 2026-08-09T13:35:47+00:00

## Health v2 (maintenance only)
Score: 66/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 8, longevity 100
- inputs: {"age_days": 2556, "days_push": 24, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 15077, forks 1749 (observed 2026-08-28T04:11:09.123068+00:00)

## What it is
Vosk is an offline open source speech recognition toolkit supporting 20+ languages with small models and a streaming API. It provides bindings for Python, Java, Node.js, C#, and more, scaling from Raspberry Pi and mobile devices to server clusters.

## Use cases
- transcribe audio to text offline
- add speech recognition to an android app
- create subtitles for movies
- transcribe lectures and interviews
- build a voice-controlled assistant or chatbot
- run speech-to-text on a raspberry pi
- identify speakers in audio recordings

## When to choose
- you need fully offline, privacy-preserving speech recognition
- you need small models that run on mobile or embedded devices
- you need streaming, low-latency transcription
- you need bindings across many programming languages

## When to avoid
- you need the highest accuracy cloud-grade ASR and have internet access
- you need languages not covered by available Vosk models
- you need built-in text-to-speech rather than recognition

## Facets
- artifact type: library
- maturity: stable
- function: speech-recognition, machine-learning, audio-processing, sdk
- domain: speech-processing, machine-learning, privacy
- platform: python, cross-platform, cli, embedded
- tags: asr, speech-to-text, offline, kaldi, streaming-transcription, speaker-identification, raspberry-pi, self-hosted, natural-language-processing, android, ios, nodejs

## Member repositories
- alphacep/vosk-api (main) score 66
- alphacep/vosk-server (backend) score 47

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:09.123068+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:06:44.870190+00:00, confidence not recorded.
  - readme: https://github.com/alphacep/vosk-api (fetched 2026-08-28T04:11:09.123068+00:00, sha 5f56ab2addce)
- Data as of 2026-08-30T08:39:29.467469+00:00.