ChatTTS

1、从 GitHub 克隆代码

git clone https://github.com/2noise/ChatTTS.git

2、安装依赖：

pip install -r requirements.txt

3、快速开始

导入必要的库：

import ChatTTS
from IPython.display import Audio
import torchaudio

初始化 ChatTTS：

chat = ChatTTS.Chat()
chat.load_models(compile=False) # 设置为 True 以获得更快的性能

准备文本：

texts = [“Hello, welcome to ChatTTS!”]

生成语音：

wavs = chat.infer(texts, use_decoder=True)
torchaudio.save(“output.wav”, torch.from_numpy(wavs[0]), 24000)
Audio(wavs[0], rate=24000, autoplay=True)

进阶用法

随机采样说话人

rand_spk = chat.sample_random_speaker()
params_infer_code = {‘spk_emb’: rand_spk, ‘temperature’: 0.3, ‘top_P’: 0.7, ‘top_K’: 20}
wavs = chat.infer(texts, params_infer_code=params_infer_code)

手动控制句子级别的韵律

params_refine_text = {‘prompt’: ‘[oral_2][laugh_0][break_6]’}
wavs = chat.infer(texts, params_refine_text=params_refine_text, params_infer_code=params_infer_code)

完整示例代码

import torch
import ChatTTS
from IPython.display import Audio
import torchaudio

# 初始化 ChatTTS
chat = ChatTTS.Chat()
chat.load_models()

# 定义文本
texts = [“Hello, welcome to ChatTTS!”]

# 生成语音
wavs = chat.infer(texts, use_decoder=True)

# 保存生成的语音
torchaudio.save(“output.wav”, torch.from_numpy(wavs[0]), 24000)

# 播放生成的语音
Audio(wavs[0], rate=24000, autoplay=True)