---
title: "The best way to run speech-to-text on Apple silicon"
description: "MLX, Core ML on the Neural Engine, whisper.cpp, WhisperKit, FluidAudio and Apple's SpeechAnalyzer compared: which engine and model to use on an M-series Mac."
canonical: "https://www.fermionresearch.com/speech/best-speech-to-text-for-apple-silicon/"
source: "Fermion Research"
---

Speech recognition/facts checked 13 November 2026

# The best way to run speech-to-text on Apple silicon

An M-series Mac has three places to run a speech model: the CPU, the GPU and the Neural Engine. The tool you pick decides which one does the work, and which models you can use.

[Speech recognition docs](https://www.fermionresearch.com/docs/speech/)

## The short answer

For a Python script or a command line on a Mac, use an MLX tool (mlx-whisper, mlx-audio, or the fermion package for the Phonon models), which runs the model on the GPU; for a Swift app that should leave the GPU free, use a Core ML package on the Neural Engine, such as WhisperKit for Whisper, FluidAudio for Parakeet, or the Phonon-2 Core ML package. whisper.cpp does both from C/C++, and Apple's own SpeechAnalyzer is built into macOS and iOS 26.

The model matters as much as the engine. Whisper gives 99 languages; Parakeet TDT 0.6B v3 and Phonon-2.5 give 25 European languages; Parakeet v2, Phonon-2.5 English and Phonon-2 are English only.

## Options compared

Facts from each project's own README or documentation, read 2026-11-13.

| Tool | Runs on | Models | Best for | Install |
| --- | --- | --- | --- | --- |
| mlx-whisper | GPU (MLX) | Whisper, any size; optional 4-bit conversion | Python scripts | pip install mlx-whisper |
| mlx-audio | GPU (MLX) | Whisper, Parakeet, Voxtral, Qwen3-ASR, Canary, Moonshine, Phonon-2 and 2.5, others | Trying many models from one package | pip install -U mlx-audio |
| fermion (Phonon) | GPU (MLX); CPU engine also available | Phonon-2.5 (25 languages), Phonon-2.5 English, Phonon-2 | Small models, CLI and an OpenAI-compatible local server | pip install fermion-research |
| Phonon-2 Core ML | Neural Engine | Phonon-2 (English) | Mac apps that keep the GPU free | Swift and Python runners on GitHub |
| whisper.cpp | GPU (Metal); encoder on the Neural Engine via Core ML | Whisper tiny to large | C/C++ apps, many language bindings | build from source |
| WhisperKit | Apple silicon, Swift | Whisper tiny to large-v3 turbo | Swift apps on macOS 14 or later | Swift Package Manager; brew install whisperkit-cli |
| FluidAudio | Neural Engine (Core ML) | Parakeet TDT v3 (25 European languages and Japanese), v2 (English) | Swift apps that also need diarization or VAD | Swift Package Manager or CocoaPods |
| SpeechAnalyzer (Apple) | built into the OS | Apple's own models | Apps on iOS, iPadOS and macOS 26 or later | Speech framework |

## GPU, Neural Engine or CPU

- GPU through MLX: the simplest path from Python, and fast. Phonon-2 runs at 174 times realtime on the GPU of a base M5 MacBook Air through MLX (Phonon-2's published figure).
- Neural Engine through Core ML: the right place for an app that runs all day, because it leaves the GPU and most of the CPU free. Phonon-2 Core ML runs at 606 times realtime on the same M5 MacBook Air (Phonon-2's published figure). FluidAudio's README gives about 190 times realtime for Parakeet on an M4 Pro, its own figure on a different machine, so the two are not a head-to-head.
- CPU: works everywhere, slower. Phonon-2 runs at 40 times realtime on the CPU of an M5 MacBook Air (published figure). whisper.cpp also runs on the CPU.

## Setup in one minute

Whisper through MLX, and Phonon through the fermion package, from a terminal on an Apple silicon Mac:

```text
# Whisper on MLX (needs ffmpeg: brew install ffmpeg)
pip install mlx-whisper
mlx_whisper audio_file.mp3

# Phonon on MLX
pip install "fermion-research[mlx]"
fermion transcribe phonon-2.5 meeting.wav
fermion transcribe phonon-2.5-en meeting.wav --json
```

## Caveats

- Whisper on any engine is the same model: the engine changes speed and memory, not the error rate. To lower the error, change the model.
- The fermion transcribe command reads wav, flac, ogg and aiff; for mp3 and m4a it prints the ffmpeg command to convert first.
- A Phonon-2.5 Core ML package is not public yet; Phonon-2.5 runs on Apple silicon through MLX today.
- If you only want dictation into any app rather than a library, Detta, our Mac dictation app, runs speech recognition on the Neural Engine. It asks for a Google sign-in, and sharing dictations to improve our models is on by default with an off switch in Settings.

## Questions

## Related

- [Speech recognition on the Apple Neural Engine with Core ML](https://www.fermionresearch.com/models/phonon-2/core-ml/)
- [On-device speech-to-text for apps](https://www.fermionresearch.com/speech/on-device-speech-to-text-for-apps/)
- [Detta now runs on the Neural Engine](https://www.fermionresearch.com/research/detta-neural-engine/)
- [Offline speech recognition in Python](https://www.fermionresearch.com/speech/offline-speech-recognition-python/)
- [Phonon-2](https://www.fermionresearch.com/models/phonon-2/)

## Sources and method

- mlx-whisper: github.com/ml-explore/mlx-examples/tree/main/whisper, read 2026-11-13. mlx-audio: github.com/Blaizzy/mlx-audio, read 2026-11-13.
- whisper.cpp: github.com/ggml-org/whisper.cpp, read 2026-11-13. WhisperKit: github.com/argmaxinc/WhisperKit, read 2026-11-13. FluidAudio (including its 190x M4 Pro figure): github.com/FluidInference/FluidAudio, read 2026-11-13.
- SpeechAnalyzer and SpeechTranscriber: developer.apple.com/documentation/speech/speechanalyzer, read 2026-11-13.
- Phonon-2 speed: Phonon-2 model page, published figures, base M5 MacBook Air 16 GB. No Phonon-2.5 speed figures are published.
- FLEURS numbers: Fermion Research measurement on the full FLEURS test set of each language, one scoring code and normalisation for every model (Phonon-2.5 release post, 2026-10-22).

Canonical: https://www.fermionresearch.com/speech/best-speech-to-text-for-apple-silicon/

Source: [https://www.fermionresearch.com/speech/best-speech-to-text-for-apple-silicon/](https://www.fermionresearch.com/speech/best-speech-to-text-for-apple-silicon/)
