Chatterbox Multilingual

This first-party Soniqo page documents Chatterbox Multilingual from the local speech-swift / speech-core implementation. Hugging Face bundles are linked below after the integration notes.

Internal Page First

Landing cards and docs menus now point here first; source model and bundle links remain available from this page.

At a Glance

Model	Chatterbox Multilingual
Role	Multilingual zero-shot voice-cloning TTS
Backend	MLX fp16 on Apple; LiteRT default-voice runtime in Speech Core
Output	24 kHz mono waveform
Languages	23 languages
License	MIT
Status	MLX cloning runtime; LiteRT greedy/default-voice runtime for edge deployments
Source	Resemble AI Chatterbox
Swift product	`ChatterboxTTS`
CLI / runtime	Programmatic speech-swift runtime; LiteRT example CLI in speech-core/examples/litert

Use

The snippet below mirrors the current speech-swift API or command exposed by the repo.

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"
)

Model Links

Implementation Notes

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.