Kokoro-82M-CoreML

End-to-end CoreML export of [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) at FP16, optimized for Apple Neural Engine. Requires iOS 18+ / macOS 15+. A single `kokoro_5s.mlmodelc` runs the full pipeline (BERT → duration prediction → fixed-shape alignment → prosody → decoder) in one CoreML call. G2P (grapheme-to-phoneme) is a separate pair of CoreML models. Looking for a smaller variant? See [`aufklarer/Kokoro-82M-CoreML-INT8`](https://huggingface.co/aufklarer/Kokoro-82M-CoreML-INT8) — INT8 k-means palettized, 83 MB vs 325 MB here, with log-spec distance 0.42 vs this FP16 reference on a validation utterance. 54 preset voices across 10 languages: English (US/UK), Spanish, French, Hindi, Italian, Japanese, Korean, Portuguese, Chinese. Add [speech-swift](https://github.com/soniqo/speech-swift) to `Package.swift`: .package(url: "https://github.com/soniqo/speech-swift", branch: "main") Then synthesize: import KokoroTTS let tts = try await KokoroTTSModel.fromPretrained( modelId: "aufklarer/Kokoro-82M-CoreML" ) let audio = try await tts.synthesize( "Hello world, this is a Kokoro test.", voice: "af_heart" ) CLI: swift run audio kokoro "Hello world" --voice af_heart --output out.wav - Base model: [hexgrad/Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M) (Apache-2.0) - Dictionaries and G2P: Apache-2.0 - Model weights: Apache-2.0 - CoreML conversion: Apache-2.0 - [speech-swift](https://github.com/soniqo/speech-swift) — Apple SDK - [soniqo.audio](https://soniqo.audio) — website - [MLX vs CoreML on Apple Silicon — a practical guide](https://blog.ivan.digital/mlx-vs-coreml-on-apple-silicon-a-practical-guide-to-picking-the-right-backend-and-why-you-should-f77ddea7b27a) — related blog post - [soniqo.audio/blog](https://soniqo.audio/blog) — blog