local-vosk
por sfkiwi
DevOps & CloudResumen
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
User asks: transcribe this Telegram voice message (voice_message.ogg)
- 1
Receives the .ogg audio file path
- 2
Converts audio to 16kHz mono WAV using ffmpeg
- 3
Loads the local Vosk model from ~/vosk-models
- 4
Processes the audio stream and produces a transcript
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-voskEjecuta el comando de la CLI o pega el prompt en Claude Code, Cursor, Codex o el agente de programación que uses.