Apple MLX

by Apple

Apple's array framework — runs Whisper, Phi, Llama on Apple Silicon.

TL;DR

Apple's array framework — runs Whisper, Phi, Llama on Apple Silicon.

Best for native Apple Silicon ML, including Whisper inference + training. Pricing: free.

Category
Open source
License
—
Stars
—
Last push
—
Pricing
free
Platforms
macOS

What it is

A NumPy-like array framework optimized for Apple's unified-memory GPUs. MIT.

Best for: Native Apple Silicon ML, including Whisper inference + training.
Watch out for: macOS-only; ecosystem still growing.

Install / use

pip install mlx

Features

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

Apple MLX vs Whipscribe

FeatureApple MLXWhipscribe
CategoryOpen sourceTranscription APIs
Pricingfreefree beta
Speaker diarizationNoYes
Word timestampsYesYes
StreamingNoNo
Languages9999
PlatformsmacOSWeb, API, MCP

Alternatives to Apple MLX

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.