Chatterbox Multilingual

Esta página da Soniqo documenta Chatterbox Multilingual 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	Chatterbox Multilingual
Papel	Multilingual zero-shot voice-cloning TTS
Backend	MLX fp16 on Apple; LiteRT default-voice runtime in Speech Core
Saída	24 kHz mono waveform
Idiomas	23 languages
Licença	MIT
Status	MLX cloning runtime; LiteRT greedy/default-voice runtime for edge deployments
Fonte	Resemble AI Chatterbox
Produto Swift	`ChatterboxTTS`
CLI / runtime	Programmatic speech-swift runtime; LiteRT example CLI in speech-core/examples/litert

Uso

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

import ChatterboxTTS

let model = try await ChatterboxTTSModel.fromPretrained()
let pcm = try model.clone(
    referenceSamples: reference,
    sampleRate: 24_000,
    text: "The cloned voice now speaks a new sentence.",
    languageId: "en"
)

Links do modelo

Notas de implementação

Download is split between the main Chatterbox bundle and the separate S3 tokenizer repository.
Pipeline is T3 text-to-speech tokens, S3Gen flow mel decoder, then HiFi-GAN / HiFTGenerator vocoder.
Reference clips are resampled to 24 kHz for S3Gen and 16 kHz for speaker/token conditioning.
speech-core's LiteRT path ships a default voice; fp16 T3 is recommended for Arabic quality.