Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

MLX Whisper — measured AI agent skill | DecimalAI

sundial-org/mlx-whisper

SkillScore100Maintained

Local speech-to-text with MLX Whisper (Apple Silicon optimized, no API key).

AI/MLby sundial-org

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

AI Engineer pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/sundial-org-mlx-whisper/SKILL.md

decimalai skills pull sundial-org-mlx-whisper --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/sundial-org-mlx-whisper/SKILL.md https://app.decimal.ai/s/sundial-org-mlx-whisper/SKILL.md

Raw file: /s/sundial-org-mlx-whisper/SKILL.md ↗ · machine-readable summary at /s/sundial-org-mlx-whisper.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 4h ago

Yes — +27% lift-18% tokens0% turns100% of whole cases pass with skill (22/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-01	✗→✓	▲ Improved	-16%	0%
case-03	✗→✓	▲ Improved	-16%	0%
case-09	✗→✓	▲ Improved	-44%	0%
case-16	✗→✓	▲ Improved	31%	0%
case-20	✗→✓	▲ Improved	-36%	0%

Showing 5 of 22 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

sundial-org / awesome-openclaw-skills

skills/mlx-whisper/SKILL.md

View on GitHub ↗

Imported 8/3/2026Version v1

Skill contents

SKILL.md

MLX Whisper

Local speech-to-text using Apple MLX, optimized for Apple Silicon Macs.

Quick Start

bash
mlx_whisper /path/to/audio.mp3 --model mlx-community/whisper-large-v3-turbo

Common Usage

bash
# Transcribe to text file
mlx_whisper audio.m4a -f txt -o ./output

# Transcribe with language hint
mlx_whisper audio.mp3 --language en --model mlx-community/whisper-large-v3-turbo

# Generate subtitles (SRT)
mlx_whisper video.mp4 -f srt -o ./subs

# Translate to English
mlx_whisper foreign.mp3 --task translate

Models (download on first use)

| Model | Size | Speed | Quality | |-------|------|-------|---------| | mlx-community/whisper-tiny | ~75MB | Fastest | Basic | | mlx-community/whisper-base | ~140MB | Fast | Good | | mlx-community/whisper-small | ~470MB | Medium | Better | | mlx-community/whisper-medium | ~1.5GB | Slower | Great | | mlx-community/whisper-large-v3 | ~3GB | Slowest | Best | | mlx-community/whisper-large-v3-turbo | ~1.6GB | Fast | Excellent (Recommended) |

Notes

Requires Apple Silicon Mac (M1/M2/M3/M4)
Models cache to ~/.cache/huggingface/
Default model is mlx-community/whisper-tiny; use --model mlx-community/whisper-large-v3-turbo for best results

Want to see if sundial-org/mlx-whisper would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.