Aller au contenu
TakoAPI
Retour aux skills

local-vosk

par sfkiwi

DevOps & Cloud
769Téléchargements rapportés par clawskills.sh
1Vues
0 mention J'aimeConnecte-toi pour aimer ce skill
—Pas encore noté
Ta note

Résumé

Local speech-to-text using Vosk.

Description

Ce que fait ce skill

Runs speech-to-text locally using the Vosk toolkit. Works fully offline after a one-time model download and supports any audio format ffmpeg can decode. No API keys, accounts, or cloud services needed.

Unlike cloud STT services, it processes audio locally with no usage costs, no data sent to third parties, and no API rate limits.

Quand l'utiliser

  • Transcribing Telegram .ogg voice messages
  • Converting recorded meeting audio to text
  • Batch transcribing audio files without internet access
  • Processing mp3, wav, m4a, and webm formats locally
  • Offline transcription on restricted or air-gapped machines

Exemple de workflow

ENTRÉE

User asks: transcribe this Telegram voice message (voice_message.ogg)

AGENT
  1. 1

    Receives the .ogg audio file path

  2. 2

    Converts audio to 16kHz mono WAV using ffmpeg

  3. 3

    Loads the local Vosk model from ~/vosk-models

  4. 4

    Processes the audio stream and produces a transcript

SORTIE

Plain text transcript of the voice message

Prérequis

  • vosk Python package
  • Vosk language model downloaded from alphacephei.com/vosk/models

Installation

clawhub install sfkiwi/local-vosk

Exécute la commande CLI, ou colle l'instruction dans Claude Code, Cursor, Codex ou l'agent de code que tu utilises.

Liens