Text-to-Speech
coqui

how to save clone voice ?

#101
by ruibin001 - opened

outputs = model.synthesize(
    "It took me quite a long time to develop a voice and now that I have it I am not going to be silent.",
    config,
    speaker_wav="/data/TTS-public/_refclips/3.wav",
    gpt_cond_len=3,
    language="en",
)

how to deal outputs to save it as wav file ?

@ruibin001 you can use the following code to achieve it:

import numpy as np
import scipy.io.wavfile as wavfile

def save_wav(wav: np.ndarray, sample_rate: int = 24000, filename='output.wav') -> None:
    wav_norm = wav * (32767 / max(0.01, np.max(np.abs(wav))))
    wav_norm = wav_norm.astype(np.int16)
    
    wavfile.write(filename=filename, rate=sample_rate, data=wav_norm)

save_wav(outputs["wav"])

Sign up or log in to comment