MLX Whisper
by Apple ML Research
Whisper inference on Apple Silicon via Apple's MLX framework.
Looking at MLX Whisper? Try this first.
Drop your audio. Transcript in seconds. First transcript free, then $4 = 300 min
TL;DR
Best for m-series Macs that want unified-memory acceleration without CoreML conversion. Pricing: free.
Category
Open source
License
MIT
Stars
★ 8.9k
Last push
2026-04-06
Pricing
free
Platforms
macOS
What it is
The Whisper example inside Apple's official MLX repo. Runs FP16/INT4 quantized models on the unified-memory GPU of M1/M2/M3 chips. MIT-licensed; integrates directly with Python and Swift MLX bindings.
Best for: M-series Macs that want unified-memory acceleration without CoreML conversion.
Watch out for: Apple Silicon only; smaller community than whisper.cpp; quantization options narrower.
Watch out for: Apple Silicon only; smaller community than whisper.cpp; quantization options narrower.
Install / use
pip install mlx-whisperFeatures
| Speaker diarization | No |
| Word-level timestamps | Yes |
| Streaming / real-time | No |
| Languages supported | 99 |
| HIPAA eligible | No |
Links
MLX Whisper vs Whipscribe
| Feature | MLX Whisper | Whipscribe |
|---|---|---|
| Category | Open source | Transcription APIs |
| Pricing | free | $4–$24 one-time packs (credits never expire) · $2 single unlock · 60 min free on signup |
| Speaker diarization | No | Yes |
| Word timestamps | Yes | Yes |
| Streaming | No | No |
| Languages | 99 | 99 |
| Platforms | macOS | Web, API, MCP |
Alternatives to MLX Whisper
Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.