当前位置：首页 > news >正文

轻松实现文字转语音 - Coqui TTS部署实践

news 来源：原创 2025/4/22 14:59:30

废话不多说，咱们直接开始吧！

环境安装

1、创建python虚拟环境

conda create --name env_coqui python=3.10
conda activate env_coqui

2、安装tts

pip install TTS

3、查看模型列表

tts --list_models
(env_coqui) PS D:\work\ai\tts\Coqui> tts --list_models

Name format: type/language/dataset/model
1: tts_models/multilingual/multi-dataset/xtts_v2
2: tts_models/multilingual/multi-dataset/xtts_v1.1
3: tts_models/multilingual/multi-dataset/your_tts
4: tts_models/multilingual/multi-dataset/bark
5: tts_models/bg/cv/vits
6: tts_models/cs/cv/vits
7: tts_models/da/cv/vits
8: tts_models/et/cv/vits
9: tts_models/ga/cv/vits
10: tts_models/en/ek1/tacotron2
11: tts_models/en/ljspeech/tacotron2-DDC
12: tts_models/en/ljspeech/tacotron2-DDC_ph
13: tts_models/en/ljspeech/glow-tts
14: tts_models/en/ljspeech/speedy-speech
15: tts_models/en/ljspeech/tacotron2-DCA
16: tts_models/en/ljspeech/vits
17: tts_models/en/ljspeech/vits–neon
18: tts_models/en/ljspeech/fast_pitch
19: tts_models/en/ljspeech/overflow
20: tts_models/en/ljspeech/neural_hmm
21: tts_models/en/vctk/vits

测试预训练模型

选择一个预训练模型（例如 tts_models/en/ljspeech/tacotron2-DDC），并测试其效果：

tts --text "Hello, this is a test of Coqui TTS." --model_name tts_models/en/ljspeech/tacotron2-DDC --vocoder_name vocoder_models/universal/libri-tts/wavegrad --out_path output.wav

上述命令运行完成后，在当前目录下生成了output.wav文件，点击可以播放。

写一个web页面

为了方便使用，我们使用flask框架做一个简单的web应用。

一段简单的python代码：

tts_demo.py
from flask import Flask, request, send_file, render_template
from TTS.api import TTS
import os
import torchapp = Flask(__name__)
# 修复 TTS 模型和 vocoder 的设置方式
from TTS.utils.radam import RAdam
from collections import defaultdict
with torch.serialization.safe_globals([RAdam, defaultdict, dict]):tts = TTS(model_name="tts_models/zh-CN/baker/tacotron2-DDC-GST")@app.route("/", methods=["GET"])
def index():return render_template("index.html")@app.route("/synthesize", methods=["POST"])
def synthesize():text = request.json.get("text")output_path = "output.wav"tts.tts_to_file(text=text, file_path=output_path)return send_file(output_path, mimetype="audio/wav")if __name__ == "__main__":app.run(host="0.0.0.0", port=5000)

一个无比简洁优雅的web页面~

templates/index.html
<!DOCTYPE html>
<html lang="zh">
<head><meta charset="UTF-8"><meta name="viewport" content="width=device-width, initial-scale=1.0"><title>文字转语音</title><style>body {font-family: Arial, sans-serif;max-width: 800px;margin: 0 auto;padding: 20px;line-height: 1.6;}h1 {text-align: center;margin-bottom: 30px;color: #333;}.container {background-color: #f9f9f9;border-radius: 8px;padding: 20px;box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);}textarea {width: 100%;height: 150px;margin-bottom: 20px;padding: 10px;border: 1px solid #ddd;border-radius: 4px;resize: vertical;}button {background-color: #4CAF50;color: white;border: none;padding: 10px 20px;text-align: center;font-size: 16px;cursor: pointer;border-radius: 4px;}button:hover {background-color: #45a049;}.audio-container {margin-top: 20px;}</style>
</head>
<body><h1>文字转语音</h1><div class="container"><textarea id="textInput" placeholder="请输入要转换为语音的文字..."></textarea><button id="convertBtn">转换为语音</button><div class="audio-container"><audio id="audioOutput" controls style="display: none;"></audio></div></div><script>document.getElementById('convertBtn').addEventListener('click', async () => {const text = document.getElementById('textInput').value;if (!text) {alert('请输入文字内容！');return;}try {// 显示加载中状态document.getElementById('convertBtn').disabled = true;document.getElementById('convertBtn').textContent = '处理中...';// 发送请求到后端const response = await fetch('/synthesize', {method: 'POST',headers: {'Content-Type': 'application/json',},body: JSON.stringify({ text })});if (!response.ok) {throw new Error('转换失败');}// 获取音频blobconst blob = await response.blob();const audioUrl = URL.createObjectURL(blob);// 播放音频const audioElement = document.getElementById('audioOutput');audioElement.src = audioUrl;audioElement.style.display = 'block';audioElement.play();} catch (error) {alert('转换失败：' + error.message);} finally {// 恢复按钮状态document.getElementById('convertBtn').disabled = false;document.getElementById('convertBtn').textContent = '转换为语音';}});</script>
</body>
</html>

运行程序：python demo.py
然后在浏览器输入访问地址：http://localhost:5000/，就可以将任意的文字转为语音啦！
在这里插入图片描述