mirror of https://github.com/coqui-ai/TTS.git
19 lines
960 B
Python
19 lines
960 B
Python
import torch
|
|
from TTS.api import TTS
|
|
|
|
# Get device
|
|
device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
|
|
# List available 🐸TTS models
|
|
print(TTS().list_models())
|
|
|
|
# Init TTS
|
|
tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)
|
|
|
|
# Run TTS
|
|
# ❗ Since this model is multi-lingual voice cloning model, we must set the target speaker_wav and language
|
|
# Text to speech list of amplitude values as output
|
|
# wav = tts.tts(text="Hello world!", speaker_wav="my/cloning/audio.wav", language="en")
|
|
# Text to speech to a file
|
|
# The tts_to_file and tts methods of TTS/api.py themselves support the speed parameter, but the internal tts method and synthesizer.tts method do not pass the speed parameter, resulting in the speed parameter being meaningless. After adding it, the speaking speed change function can be used normally.
|
|
tts.tts_to_file(text="Hello world!", speaker_wav="my/cloning/audio.wav", language="en", file_path="output.wav", speed=0.5) |