Text-to-speech overview

use gpt_sovits_mlx::VoiceCloner;

// Create voice cloner with default models
let mut cloner = VoiceCloner::with_defaults()?;

// Set reference audio for voice cloning
cloner.set_reference_audio("reference.wav")?;

// Synthesize speech
let audio = cloner.synthesize("Hello, world!")?;

// Save output
cloner.save_wav(&audio, "output.wav")?;

// Mixed language synthesis works automatically
let audio = cloner.synthesize("你好 world! 今天天气 is great!")?;