makima/src/main.rs


1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33

use std::path::Path;
use crate::tts::{save_wav, ChatterboxTTS};

mod audio;
mod listen;
pub mod tts;

fn main() -> Result<(), Box<dyn std::error::Error>> {
    println!("Loading ChatterboxTTS...");
    let tts = ChatterboxTTS::from_pretrained(None)?;
    println!("Model loaded successfully!");

    // Load reference audio from mp3
    println!("Loading reference audio...");
    let reference = audio::to_16k_mono_from_path(Path::new("audio.mp3"))?;
    let samples = &reference.samples;
    let sample_rate = reference.sample_rate;

    // Voice cloning using audio samples
    println!("Generating TTS with voice cloning...");
    let audio = tts.generate_tts_with_samples(
        "Hello, this is a test of the voice cloning system [chuckles]. Repeat after me \" I am Steve Jobs!\"",
        samples,
        sample_rate,
    )?;

    println!("Generated {} samples", audio.len());
    save_wav(&audio, Path::new("output.wav"))?;
    println!("Saved to output.wav");
    let segments = listen::listen()?;
    println!("Captured {} diarized segments", segments.len());
    Ok(())
}