Назад към всички

audio-transcribe

// Auto-transcribe voice messages using faster-whisper (local, no API key needed).

$ git log --oneline --stat
stars:1,933
forks:367
updated:March 4, 2026
SKILL.mdreadonly

Audio Transcription Skill

Auto-transcribe voice messages using faster-whisper (local, no API key needed).

Requirements

pip install faster-whisper

Models download automatically on first use.

Usage

Transcribe a file

python3 /root/clawd/skills/audio-transcribe/scripts/transcribe.py /path/to/audio.ogg

Change model (edit script)

Edit transcribe.py and change:

model = WhisperModel('small', device='cpu', compute_type='int8')  # Options: tiny, base, small, medium, large-v3

Models

ModelSizeVRAM/RAMSpeedUse Case
tiny39 MB~1 GB⚡⚡⚡Quick drafts
base74 MB~1 GB⚡⚡Basic accuracy
small244 MB~2 GBRecommended
medium769 MB~5 GB🐢Better accuracy
large-v31.5 GB~10 GB🐢🐢Best accuracy

Integration

Clawdbot auto-transcribes incoming voice messages when this skill is enabled.

Files

  • scripts/transcribe.py — Main transcription script
  • SKILL.md — This file