Skip to content

Latest commit

 

History

History
27 lines (18 loc) · 622 Bytes

README.md

File metadata and controls

27 lines (18 loc) · 622 Bytes

Soprano

A compact autoregressive text-to-speech (TTS) model for efficient local synthesis.

Hugging Face Model Repo

CLI Example

mlx-audio-swift-tts --model mlx-community/Soprano-80M-bf16 --text "Hello world."

Swift Example

import MLXAudioTTS

let model = try await SopranoModel.fromPretrained("mlx-community/Soprano-80M-bf16")
let audio = try await model.generate(
    text: "Hello world.",
    parameters: GenerateParameters()
)

Notes

  • The voice argument is currently unused in the base SopranoModel implementation.