Saltar al contenido
TakoAPI
Volver a skills

local-vosk

por sfkiwi

DevOps & Cloud
769Descargas según clawskills.sh
1Vistas
0 me gustaInicia sesión para dar me gusta a esta skill
—Aún sin valoraciones
Tu valoración

Resumen

Local speech-to-text using Vosk.

Descripción

Qué hace esta 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.

Cuándo usarla

  • 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

Flujo de trabajo de ejemplo

ENTRADA

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

AGENTE
  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

SALIDA

Plain text transcript of the voice message

Requisitos

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

Instalación

clawhub install sfkiwi/local-vosk

Ejecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.

Enlaces