Download Latest Version
v0.4.2 source code.tar.gz (4.5 MB)
Get an email when there's a new version of MLX-Audio
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-01-25 | 2.8 kB | |
| v0.3.0 source code.tar.gz | 2026-01-25 | 3.3 MB | |
| v0.3.0 source code.zip | 2026-01-25 | 3.5 MB | |
| Totals: 3 Items | 6.8 MB | 0 | |
What's Changed
- Fix speaker embedding extraction in Qwen3-TTS model by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/390
- Fix Qwen3-TTS tail artifacts by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/391
- Fix Qwen3-TTS Base Voice Cloning by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/394
- Add Vibevoice ASR by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/389
- Qwen3 speaker embedding tests by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/396
- Update TTS commands in README to include language code option by @rudolfolah in https://github.com/Blaizzy/mlx-audio/pull/401
- Unify Mimi implementation for Pocket TTS by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/403
- Fix issue of ref_audio not loading prior to inference with server. by @BuffMcBigHuge in https://github.com/Blaizzy/mlx-audio/pull/406
- Enhance README with installation and usage examples by @rahimnathwani in https://github.com/Blaizzy/mlx-audio/pull/404
- Upgrade GitHub Actions for Node 24 compatibility by @salmanmkc in https://github.com/Blaizzy/mlx-audio/pull/418
- Upgrade GitHub Actions to latest versions by @salmanmkc in https://github.com/Blaizzy/mlx-audio/pull/419
- [VibeVoice-ASR] Fix Metal kernel crash and optimize memory for long audio by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/417
- fix: Allowing quantization of Qwen3-TTS! Adding model_quant_predicate to Qwen3-TTS to exclude embedding layers by @kyr0 in https://github.com/Blaizzy/mlx-audio/pull/398
- Fix qwen3 tts quants (silence in VC and word precision) by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/407
- Fix stt array io by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/426
- Update MANIFEST.in to remove leading dot from requirements.txt path by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/428
- Move audio path/format prints under verbose flag by @wladpaiva in https://github.com/Blaizzy/mlx-audio/pull/429
- Update pyproject.toml and GitHub Actions workflow for package publishing by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/431
New Contributors
- @rudolfolah made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/401
- @BuffMcBigHuge made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/406
- @rahimnathwani made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/404
- @salmanmkc made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/418
- @kyr0 made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/398
- @wladpaiva made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/429
Full Changelog: https://github.com/Blaizzy/mlx-audio/compare/v0.2.10...v0.3.0
