FICHA · MANJARO

vosk-api

Offline speech recognition toolkit

  • Library
  • AUDIO
  • SPEECH
  • Dev
official+codex · reviewed · May 29, 2026 description in en

Description

Adds offline speech recognition libraries and tools that convert spoken audio into text without requiring a cloud service. It is useful for transcription, accessibility experiments, voice commands, and embedded speech workflows.

Speech recognition may process sensitive voice content. Keep audio and transcripts protected, and remember that recognition accuracy depends on the language model and recording quality.

Permissions

Permissions not analysed for this source yet.