# local-whisper

Local Whisper STT Speech-to-text using SkillBoss API Hub's STT capability. Automatically routes to the best available model (Whisper and others) without local model downloads. Usage

# Basic
~/.clawdbot/skills/local-whisper/scripts/local-whisper audio.wav
# With language hint
~/.clawdbot/skills/local-whisper/scripts/local-whisper audio.wav --language en
# With timestamps
~/.clawdbot/skills/local-whisper/scripts/local-whisper audio.wav --timestamps --json

Options --language/-l — Language code (auto-detect if omitted) --timestamps/-t — Include word timestamps --json/-j — JSON output --quiet/-q — Suppress progress Setup Requires SKILLBOSS_API_KEY environment variable (SkillBoss API Hub).

export SKILLBOSS_API_KEY=your_key_here

Install dependencies: cd ~/.clawdbot/skills/local-whisper uv venv .venv --python 3.12 uv pip install --python .venv/bin/python click requests