What's Changed

• Add CSM (Conversational Speech Model) section to README.md by @ivanfioravanti in https://github.com/Blaizzy/mlx-audio/pull/56
• Use MLX-based SNAC vocoder for Orpheus by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/62
• Add Descript neural audio codec by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/57
• Vectorize overlap-add operation in istft by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/66
• Align Orpheus sampling parameters with the reference implementation by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/68
• Improve Korkoro generation performance by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/73
• Add Speech to Speech Tab to the UI by @freddyaboulton in https://github.com/Blaizzy/mlx-audio/pull/79
• Add support for fp16 variant of Sesame by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/78
• Add (partially-working) voice matching support for Orpheus by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/75
• Bible Audiobook example by @andrepadez in https://github.com/Blaizzy/mlx-audio/pull/43
• removed push notification to ntfy by @andrepadez in https://github.com/Blaizzy/mlx-audio/pull/81
• Bump version by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/82

New Contributors

• @freddyaboulton made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/79

Full Changelog: https://github.com/Blaizzy/mlx-audio/compare/v0.0.3...v0.0.4