coqui-ai/TTS v0.15.0

😄 v0.15.0

on GitHub

text = "Hello, my name is Manmay , how are you?"

from TTS.tts.configs.bark_config import BarkConfig
from TTS.tts.models.bark import Bark

config = BarkConfig()
model = Bark.init_from_config(config)
model.load_checkpoint(config, checkpoint_dir="path/to/model/dir/", eval=True)

# with random speaker
output_dict = model.synthesize(text, config, speaker_id="random", voice_dirs=None)

# cloning a speaker.
# It assumes that you have a speaker file in `bark_voices/speaker_n/speaker.wav` or `bark_voices/speaker_n/speaker.npz`
output_dict = model.synthesize(text, config, speaker_id="ljspeech", voice_dirs="bark_voices/")

from TTS.api import TTS

# Load the model to GPU
# Bark is really slow on CPU, so we recommend using GPU.
tts = TTS("tts_models/multilingual/multi-dataset/bark", gpu=True)


# Cloning a new speaker
# This expects to find a mp3 or wav file like `bark_voices/new_speaker/speaker.wav`
# It computes the cloning values and stores in `bark_voices/new_speaker/speaker.npz`
tts.tts_to_file(text="Hello, my name is Manmay , how are you?",
                file_path="output.wav",
                voice_dir="bark_voices/",
                speaker="ljspeech")


# When you run it again it uses the stored values to generate the voice.
tts.tts_to_file(text="Hello, my name is Manmay , how are you?",
                file_path="output.wav",
                voice_dir="bark_voices/",
                speaker="ljspeech")


# random speaker
tts = TTS("tts_models/multilingual/multi-dataset/bark", gpu=True)
tts.tts_to_file("hello world", file_path="out.wav")