What's Changed

• Revert utils load and fix deprecate API by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/98
• Remove all remaining torch calls by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/95
• Dia: Split long inputs into individual two-speaker segments by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/100
• Dia: Avoid extra allocations in kv cache by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/103
• Add local version of Whisper for (STT) by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/105
• Add streaming support for Sesame CSM by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/107
• Add default voices for Sesame by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/109
• Fix sesame loading and add mixed_3_4 quantisation by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/113
• Add basic Modular Speech-To-Speech pipeline (CLI) by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/111
• Add Spark-TTS by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/92
• Fix SparkTTS Quant by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/120
• Update spark.py by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/121
• Add Parakeet (STT) by @Blaizzy in https://github.com/Blaizzy/mlx-audio/pull/122
• Improve Parakeet token merging by @senstella in https://github.com/Blaizzy/mlx-audio/pull/129
• Add MLX Swift Support and examples by @BenLumenDigital in https://github.com/Blaizzy/mlx-audio/pull/84
• Add wav2vec2 model (STT) for Spark by @lucasnewman in https://github.com/Blaizzy/mlx-audio/pull/131

New Contributors

• @senstella made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/129
• @BenLumenDigital made their first contribution in https://github.com/Blaizzy/mlx-audio/pull/84

Full Changelog: https://github.com/Blaizzy/mlx-audio/compare/v0.1.0...v0.2.0