Mlx Whisper
@mgreten/mlx-whisperv2026.07.16.1
01README
Transcribe audio files using mlx_whisper on Apple Silicon. Runs the mlx_whisper CLI, captures the JSON output, and stores the full transcript (segments + language) as a swamp resource for downstream pipeline steps. Requires mlx_whisper installed (pip install mlx-whisper).
02Release Notes
Rebuild against swamp CLI 20260716
03Models
@mgreten/mlx-whisperv2026.07.16.1mlx_whisper.ts
fn transcribe(audioPath: string)
Transcribe an audio file to structured JSON using mlx_whisper
| Argument | Type | Description |
|---|---|---|
| audioPath | string | Absolute path to the audio file (m4a, mp3, wav, etc.) |
Resources
transcript(infinite)— Whisper JSON transcript with full segment data
04Previous Versions
2026.06.27.1
2026.05.28.3
2026.05.28.2
2026.05.28.1
05Stats
A
100 / 100
Downloads
5
Archive size
4.9 KB
- Has README or module doc2/2earned
- README has a code example1/1earned
- README is substantive1/1earned
- Most symbols documented1/1earned
- No slow types (deprecated)1/1earned
- Dependencies pass trust audit2/2earned
- Has description1/1earned
- Platform support declared (or universal)2/2earned
- License declared1/1earned
- Verified public repository2/2earned
06Platforms
07Labels