Tools · SPBoucher
Menu

MLX Whisper

by Apple Inc. · Library · also known as mlx-whisper, mlx_whisper

Port of OpenAI's Whisper speech-recognition models to MLX, offering a CLI and Python API for local transcription on Apple Silicon

MIT licenseOpen sourceFreeLocalSelf-hostable
Visit official site Compare

Link verified Nov 2, 2026

Overview

MLX Whisper is the Whisper example from Apple's mlx-examples repository packaged as a PyPI library (mlx-whisper, MIT license). It runs OpenAI's open Whisper speech-recognition models on Apple Silicon through MLX rather than PyTorch, using pre-converted weights hosted in the mlx-community organization on the Hugging Face Hub or models you convert yourself.

The mlx_whisper command transcribes an audio file, or audio piped on standard input, into text, SRT, VTT or JSON output, with options for model choice, language and translation. The Python transcribe function returns segments and can produce word-level timestamps. ffmpeg must be installed for audio decoding. It is a convenient choice for researchers and developers who want fast local transcription of lectures, interviews or recordings without sending audio to a cloud service.

Limits are those of Whisper itself (accuracy varies by language and audio quality, no built-in speaker diarization) plus the Apple Silicon requirement; it is a focused example package rather than a full transcription product.

Capabilities

  • Local transcription of audio files or stdin streams
  • Multiple output formats including text, SRT, VTT and JSON
  • Word-level timestamps
  • Choice of Whisper model sizes from the Hugging Face Hub
  • Python API alongside the command-line tool

Typical workflows

  1. Transcribe recorded lectures or meetings on a Mac
  2. Batch-generate subtitles for a video archive
  3. Embed speech-to-text in a local Python pipeline

Strengths

  • No cloud dependency; audio stays on the machine
  • Simple pip install and single command
  • MIT license

Limitations

  • Apple Silicon only
  • No speaker diarization
  • Requires ffmpeg and model downloads
  • Maintained as an example package rather than a standalone product

Prerequisites

  • Mac with Apple Silicon
  • Python 3.8 or newer
  • ffmpeg

Who it is for

  • Researchers transcribing interviews and lectures
  • Developers adding local speech-to-text to Mac tools

Alternatives & comparison

  • MLX

    Apple's open-source array framework for machine learning on Apple Silicon, with NumPy-like Python, C++ and Swift APIs and unified CPU/GPU memory

    Open sourceOpen source
  • Whisper

    OpenAI's open-source multilingual speech recognition model family with MIT-licensed code and weights, a Python package and CLI for transcription, translation and language identification

    Open sourceOpen source
Compare MLX Whisper with its alternatives →

Sources & verification

Primary sources consulted for this record. Claims are tied to the fields each source supports; the automated link checker re-verifies every URL on a schedule.

Confidence
High
Reviewed
Nov 1, 2026
Links
Verified · Nov 2, 2026

Spotted an error?

Broken link, outdated license, wrong category, or a tool that no longer exists? Tell us; reports are reviewed by the editor.

llama.cpp

ggml-org (Georgi Gerganov and contributors) · Local LLM inference & serving

In-depth entry

C/C++ inference engine for LLMs and vision-language models with GGUF quantized weights, Metal, CUDA, Vulkan and other backends, a CLI and an OpenAI-compatible server

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

LM Studio

Element Labs, Inc. · Local LLM inference & serving

In-depth entry

Proprietary desktop app for discovering, downloading and running local LLMs with llama.cpp and MLX engines, a chat UI, an OpenAI-compatible server, CLI, SDKs and a headless daemon

ProprietaryFreemiumPaidLocalBroken

MLX LM

Apple Inc. · Apple Silicon ML & MLX

In-depth entry

Python package and CLI for running, serving, quantizing and fine-tuning large language models on Apple Silicon with MLX

MITOpen sourceFreeLocalNov 2, 2026

Ollama

Ollama · Local LLM inference & serving

In-depth entry

Open-source runtime and model manager for running open-weight LLMs locally on macOS, Windows and Linux, with a REST API, OpenAI- and Anthropic-compatible endpoints and optional cloud models

MITOpen sourceFreeLocalSelf-hostedNov 2, 2026

Core ML

Apple Inc. · Apple Silicon ML & MLX

Apple's on-device machine-learning runtime for iOS and macOS apps, with the open-source coremltools package for converting PyTorch and other models to its format

BSD-3-ClauseFreeLocalNov 2, 2026

Metal

Apple Inc. · Apple Silicon ML & MLX

Apple's low-level GPU programming framework for graphics and parallel compute on iOS, macOS and visionOS, the layer beneath MLX, Core ML and most Apple Silicon ML runtimes

ProprietaryFreeLocalNov 2, 2026