alphacep/vosk-api

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

What it solves

It provides an offline, open-source speech recognition toolkit that allows users to convert spoken language into text without needing an internet connection, supporting over 20 languages and dialects.

How it works

Vosk uses small, efficient models (around 50 MB) that enable continuous transcription of large vocabularies. It offers a streaming API for zero-latency responses and supports speaker identification and reconfigurable vocabularies.

Who it’s for

Developers building chatbots, smart home appliances, and virtual assistants, as well as those needing to create subtitles for movies or transcriptions for lectures and interviews.

Highlights

  • Offline functionality for privacy and reliability.
  • Support for 20+ languages and dialects.
  • Lightweight models (50 MB) that run on everything from Raspberry Pi to large clusters.
  • Bindings available for multiple languages including Python, Java, Node.JS, C#, C++, Rust, and Go.

Related

  • Project
    Uberi/speech_recognition

    A Python library that provides a unified interface for speech recognition, supporting multiple online and offline engines like OpenAI Whisper, Google Speech, and Vosk.

  • Project
    QuentinFuxa/WhisperLiveKit

    An ultra-low-latency, self-hosted speech-to-text pipeline that enables real-time transcription and translation using advanced simultaneous speech research and multiple model backends.

  • Project
    PierrunoYT/Kokoro-TTS-Local

    A local implementation of the Kokoro-82M text-to-speech model featuring a web interface, 54 multilingual voices, and full offline support.

  • Project
    Beingpax/VoiceInk

    A native macOS application that uses local AI models to provide instant, privacy-focused voice-to-text transcription and a conversational AI assistant.