Loading...
Loading...
Local speech-to-text using OpenAI Whisper. Runs fully offline after model download. High quality transcription with multiple model sizes.
npx skill4agent add thinkfleetai/thinkfleet-engine local-whisper# Basic
~/.thinkfleetbot/skills/local-whisper/scripts/local-whisper audio.wav
# Better model
~/.thinkfleetbot/skills/local-whisper/scripts/local-whisper audio.wav --model turbo
# With timestamps
~/.thinkfleetbot/skills/local-whisper/scripts/local-whisper audio.wav --timestamps --json| Model | Size | Notes |
|---|---|---|
| 39M | Fastest |
| 74M | Default |
| 244M | Good balance |
| 809M | Best speed/quality |
| 1.5GB | Maximum accuracy |
--model/-m--language/-l--timestamps/-t--json/-j--quiet/-q.venv/cd ~/.thinkfleetbot/skills/local-whisper
uv venv .venv --python 3.12
uv pip install --python .venv/bin/python click openai-whisper torch --index-url https://download.pytorch.org/whl/cpu