스킬로 돌아가기
local-vosk
sfkiwi 제작
DevOps & Cloud—아직 평가 없음
내 평가
요약
Local speech-to-text using Vosk.
설명
이 스킬이 하는 일
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.
사용 시점
- 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
예시 워크플로
입력
User asks: transcribe this Telegram voice message (voice_message.ogg)
에이전트
- 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
출력
Plain text transcript of the voice message
요구 사항
- vosk Python package
- Vosk language model downloaded from alphacephei.com/vosk/models
설치
clawhub install sfkiwi/local-voskCLI 명령을 실행하거나, 프롬프트를 Claude Code, Cursor, Codex 등 사용하는 코딩 에이전트에 붙여넣으세요.