Download Latest Version
v0.4.7 source code.zip (7.2 MB)
Get an email when there's a new version of MLX-Audio
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| README.md | 2026-07-09 | 3.1 kB | |
| v0.4.5 source code.tar.gz | 2026-07-09 | 6.7 MB | |
| v0.4.5 source code.zip | 2026-07-09 | 7.1 MB | |
| Totals: 3 Items | 13.9 MB | 0 | |
What's Changed
- Add ZONOS2 TTS model by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/791
- Cache Higgs v3 reference audio codes by @sxy-trans-n in https://github.com/Blaizzy/mlx-audio/pull/793
- Make sure to evaluate arrays before moving across threads by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/798
- Add support for MOSS-TTS-Local-Transformer-v1.5 by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/797
- Add Higgs v3 batch generation by @sxy-trans-n in https://github.com/Blaizzy/mlx-audio/pull/802
- Add Higgs v3 continuous batching by @sxy-trans-n in https://github.com/Blaizzy/mlx-audio/pull/804
- perf: cache ECAPA mel filters + top-k slice, remove MLX floor in sortformer by @hluaguo in https://github.com/Blaizzy/mlx-audio/pull/801
- perf(stt): hot-path profiling optimizations and memory/sync improvements by @hluaguo in https://github.com/Blaizzy/mlx-audio/pull/806
- Reduce Higgs v3 AR decode syncs by @sxy-trans-n in https://github.com/Blaizzy/mlx-audio/pull/808
- Point OmniVoice docs to the MLX-ready mlx-community/OmniVoice-bfloat16 by @Lazarus-931 in https://github.com/Blaizzy/mlx-audio/pull/807
- Higgs audio 3 stt support by @Lazarus-931 in https://github.com/Blaizzy/mlx-audio/pull/811
- Fix SineGen length alignment by @kanihal in https://github.com/Blaizzy/mlx-audio/pull/785
- Add Confucius4-TTS: multilingual zero-shot voice-cloning TTS (MLX) by @Hert4 in https://github.com/Blaizzy/mlx-audio/pull/799
- Add streaming and batching support for ZONOS2 by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/792
- [Model] Support MOSS-Transcribe-Diarize by @gcanlin in https://github.com/Blaizzy/mlx-audio/pull/812
- Prevent OOM for Nemotron ASR by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/817
- Add MOSS-Music by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/819
- feat(stt): implement segment batching for Qwen3-ASR (--max-parallel-segments) by @hhh2210 in https://github.com/Blaizzy/mlx-audio/pull/783
- Bump version to v0.4.5 by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/824
- Fix slow STT tests by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/810
- Optimize MOSS-TD audio feature injection by @sxy-trans-n in https://github.com/Blaizzy/mlx-audio/pull/823
New Contributors
- @sxy-trans-n made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/793
- @hluaguo made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/801
- @Lazarus-931 made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/807
- @kanihal made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/785
- @Hert4 made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/799
- @gcanlin made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/812
- @hhh2210 made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/783
Full Changelog: https://github.com/Blaizzy/mlx-audio/compare/v0.4.4...v0.4.5