Awesome-openclaw-skills parakeet-mlx
Local speech-to-text with Parakeet MLX (ASR) for Apple Silicon (no API key).
install
source · Clone the upstream repo
git clone https://github.com/sundial-org/awesome-openclaw-skills
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/sundial-org/awesome-openclaw-skills "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/parakeet-mlx" ~/.claude/skills/sundial-org-awesome-openclaw-skills-parakeet-mlx && rm -rf "$T"
OpenClaw · Install into ~/.openclaw/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/sundial-org/awesome-openclaw-skills "$T" && mkdir -p ~/.openclaw/skills && cp -r "$T/skills/parakeet-mlx" ~/.openclaw/skills/sundial-org-awesome-openclaw-skills-parakeet-mlx && rm -rf "$T"
manifest:
skills/parakeet-mlx/SKILL.mdsource content
Parakeet MLX (CLI)
Use
parakeet-mlx to transcribe audio locally on Apple Silicon.
Quick start
parakeet-mlx /path/audio.mp3 --output-format txtparakeet-mlx /path/audio.m4a --output-format vtt --highlight-wordsparakeet-mlx *.mp3 --output-format all
Notes
- Install CLI with:
(notuv tool install parakeet-mlx -U
oruv add
)pip install - Use
to see all options (parakeet-mlx --help
, not--help
).-h - Models download from Hugging Face to
on first run.~/.cache/huggingface - Default model:
(optimized for Apple Silicon).mlx-community/parakeet-tdt-0.6b-v3 - Requires
installed for audio processing.ffmpeg - Output formats: txt, srt, vtt, json, or all.
- Use
for detailed progress and confidence scores.--verbose - Accepts multiple files (shell wildcards like
work).*.mp3