MLX Whisper

by Apple ML Research

Whisper inference on Apple Silicon via Apple's MLX framework.

TL;DR

Whisper inference on Apple Silicon via Apple's MLX framework.

Best for m-series Macs that want unified-memory acceleration without CoreML conversion. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
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.

Install / use

pip install mlx-whisper

Features

Speaker diarizationNo
Word-level timestampsYes
Streaming / real-timeNo
Languages supported99
HIPAA eligibleNo

MLX Whisper vs Whipscribe

FeatureMLX WhisperWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsmacOSWeb, API, MCP

Alternatives to MLX Whisper

OpenAI Whisper
OpenAI

The reference open-source multilingual ASR model from OpenAI.

OSS · MIT ★ 98.1k
whisper.cpp
Georgi Gerganov

C/C++ port of Whisper — runs on anything, from a Raspberry Pi to Apple Silicon.

OSS · MIT ★ 48.8k
faster-whisper
SYSTRAN

4× faster than reference Whisper using CTranslate2 — production sweet spot.

OSS · MIT ★ 22.3k

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.