# Mlx Whisper

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

- Skill: `dvcrn/mlx-whisper-2` (Agent Skill)
- Install (CLI): `npx skillmds@latest add dvcrn/mlx-whisper-2`
- Raw SKILL.md: https://api.skillmd.com/api/skills/dvcrn/mlx-whisper-2/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Integrations & APIs
- Author: dvcrn (https://skillmd.com/u/dvcrn)
- Updated: 2026-09-09
- Page: https://skillmd.com/skills/dvcrn/mlx-whisper-2

---


# 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
```

Always pass `--model mlx-community/whisper-large-v3-turbo`, unless the user explicitly asks for a different model.

## 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
```

## Notes

- Requires Apple Silicon Mac (M1/M2/M3/M4)
- Models cache to `~/.cache/huggingface/`