Skip to main content
Public
Blaizzy Blaizzy
whisper 10 items
..
Go back to parent directory
assets
Jan 25, 2026
FOLDER Last modified by Blaizzy
tests
Jan 25, 2026
FOLDER Last modified by Blaizzy
__init__.py 177 B
Jan 25, 2026
PY Last modified by Blaizzy
audio.py 2.39 KB
Jan 25, 2026
PY Last modified by Blaizzy
decoding.py 28.37 KB
Jan 25, 2026
PY Last modified by Blaizzy
streaming.py 9.83 KB
Jan 25, 2026
PY Last modified by Blaizzy
timing.py 10.63 KB
Jan 25, 2026
PY Last modified by Blaizzy
tokenizer.py 12.12 KB
Jan 25, 2026
PY Last modified by Blaizzy
whisper.py 47.67 KB
Jan 25, 2026
PY Last modified by Blaizzy
writers.py 9.9 KB
Jan 25, 2026
PY Last modified by Blaizzy
About

MLX-Audio is an open-source audio AI framework for fast text-to-speech, speech-to-text, and speech-to-speech processing, optimized for Apple Silicon using MLX.

383 files
88 folders
7.11 MB total size
0 open issues
0 open pull requests
0 watchers
0 forks
0 stars
676 views
Updated Jan 25, 2026
Recent Commits View all
user
Initial commit - Upload project 'mlx-audio'
Blaizzy committed Jan 25, 2026
Languages
Python 95.1%
TypeScript 4.4%
YAML 0.2%
Text 0.2%
CSS 0.1%
TOML 0.1%
LICENSE 0.0%
JavaScript 0.0%
INI 0.0%
__init__ 0.0%