Supertonic-3
此 Soniqo 页面记录本地 speech-swift / speech-core 实现中的 Supertonic-3。Hugging Face 包链接放在集成说明之后。
先进入站内页面
首页卡片和文档菜单先指向这里;源模型和权重包链接仍在本页提供。
概览
| 模型 | Supertonic-3 |
|---|---|
| 用途 | G2P-free multilingual text-to-speech |
| 后端 | CoreML (Apple Neural Engine / GPU) and LiteRT |
| 输出 | 44.1 kHz mono Float32 PCM |
| 语言 | 31 languages plus a neutral na tag |
| 许可证 | OpenRAIL-M weights, MIT code |
| 状态 | Ready for CoreML; LiteRT reference implementation in speech-core |
| 来源 | Supertone Supertonic-3 |
| Swift 产品 | SupertonicTTS |
| CLI / 运行时 | Shared TTS pipeline / server integration; LiteRT C++ wrapper for edge runtimes |
使用
下面的片段对应当前 speech-swift 仓库暴露的 API 或命令。
import SupertonicTTS
let tts = try await SupertonicTTSModel.fromPretrained()
let pcm = try tts.synthesize(
text: "Hello from an on-device voice.",
voiceId: "F1",
language: "en"
)
模型链接
实现说明
- 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.