Registry / ai-ml / mlx-whisper

mlx-whisper

JSON →
library0.4.3pypypiunverified

mlx-whisper is a fast implementation of OpenAI's Whisper model optimized for Apple Silicon (M1/M2/M3) using Apple's MLX framework. Version 0.4.3 supports transcription, language detection, and word-level timestamps with Hugging Face Hub integration. Updates are frequent, roughly weekly.

ai-mlllm-agents
pip install mlx-whisper
github ↗package ↗
INSTALL
IMPORT
SIG · MLX-WHISPER
M
mlx-whisper
ai-mlpythonv0.4.3
Install
80.2s avg
Import
—
Disk
5222MB
Pass rate
4/ 10
Env Coverage4 / 10
glibc
3.9–3.13
musl
3.9–3.13
Install & Compatibility
Where this runs
tested against v0.4.3 · pip install
no network on importno background threads
Install × environment matrix
Each cell = how many times install + import succeeded across repeated harness runs. Partial = flaky.
glibc = Debian/Ubuntu slim · musl = Alpine Linux
musl
glibc
py 3.10
✕ build_error
✓ 91.7s
py 3.11
✕ build_error
✓ 82.8s
py 3.12
✕ build_error
✓ 78.1s
py 3.13
✕ build_error
✓ 68s
py 3.9
✕ build_error
✕ timeout
5222MB installed
● package 5222MB
Code
Verified usage

Verified import paths — ran on the pinned version, not inferred.

load_audio
✓ from mlx_whisper import load_audio
✗ from mlx_whisper import load_audio

Transcribe an audio file (supported formats: .mp3, .wav, .m4a, .flac, .ogg).

from mlx_whisper import transcribe result = transcribe("audio.mp3") print(result["text"])
mlx_whisper --version
Debug
Known issues
gotchamlx-whisper only works on Apple Silicon (arm64). It will fail on Intel Macs or non-Apple hardware with cryptic import errors about missing MLX.
fix
Run on an Apple Silicon machine (M1/M2/M3/M4) or use a different Whisper implementation.
affects: all
gotchaThe audio file path must be a local file or a URL. Some users incorrectly pass a bytes/ndarray object; transcribe expects a file path string.
fix
Provide a valid file path (e.g., 'audio.mp3') or download the file first.
affects: all
breakingIn version 0.4.0, the return type of transcribe() changed from a dict with key 'segments' to a more detailed dict with 'text', 'segments', 'language', etc. Old code accessing e.g. result['segments'][0]['text'] still works, but result['text'] is now available.
fix
Update code to use the new keys. Old code is backward-compatible but you may want to use the streamlined result['text'].
affects: >=0.4.0
deprecatedThe function `mlx_whisper.transcribe()` no longer accepts `group_segments=True` (removed in 0.3.0). Pass `word_timestamps=True` for word-level timestamps.
fix
Use `word_timestamps=True` instead of `group_segments=True`.
affects: >=0.3.0
Upgrade
Version history
0.4.3latest on PyPI · released Aug 29, 2025
Audit
Dependencies
mlxrequiredRequired; MLX is the core machine learning framework.
numpyrequiredRequired for audio processing.
huggingface_hubrequiredRequired for downloading models from Hugging Face Hub.
Agent activity
20 hits · last 30 days
node
18
OpenAI (training)
1
Resources
githubhttps://github.com/ml-explore/mlx-examples ↗
packagehttps://pypi.org/project/mlx-whisper/ ↗