Supertonic-3

Esta página da Soniqo documenta Supertonic-3 conforme a implementação local em speech-swift / speech-core. Os links do Hugging Face ficam abaixo das notas de integração.

Página interna primeiro

Cards e menus apontam primeiro para cá; os links do modelo fonte e dos bundles continuam disponíveis nesta página.

Visão geral

Modelo	Supertonic-3
Papel	G2P-free multilingual text-to-speech
Backend	CoreML (Apple Neural Engine / GPU) and LiteRT
Saída	44.1 kHz mono Float32 PCM
Idiomas	31 languages plus a neutral na tag
Licença	OpenRAIL-M weights, MIT code
Status	Ready for CoreML; LiteRT reference implementation in speech-core
Fonte	Supertone Supertonic-3
Produto Swift	`SupertonicTTS`
CLI / runtime	Shared TTS pipeline / server integration; LiteRT C++ wrapper for edge runtimes

Uso

O trecho abaixo reflete a API ou comando atual exposto por speech-swift.

import SupertonicTTS

let tts = try await SupertonicTTSModel.fromPretrained()
let pcm = try tts.synthesize(
    text: "Hello from an on-device voice.",
    voiceId: "F1",
    language: "en"
)

Links do modelo

Notas de implementação

No espeak, phonemizer, or lexicon: text is NFKD-normalized and mapped through a Unicode index table.
Download uses explicit CoreML package globs for the four graphs plus tokenizer, config, and voice style JSON files.
The Apple export uses dynamic latent length; the current LiteRT path uses fixed graph shapes and chunks longer text.
Voices are precomputed style presets F1-F5 and M1-M5; on-device cloning is out of scope because the style extractor is not released.