Spaces:
Paused
Paused
File size: 3,980 Bytes
76374ce 03641be 76374ce 03641be 76374ce |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 |
# server.py
from flask import Flask, request, send_file, jsonify, render_template_string
from gevent.pywsgi import WSGIServer
from dotenv import load_dotenv
import os
from tts_handler import generate_speech, get_models, get_voices
from utils import require_api_key, AUDIO_FORMAT_MIME_TYPES
app = Flask(__name__)
load_dotenv()
API_KEY = os.getenv('API_KEY', 'your_api_key_here')
PORT = int(os.getenv('PORT', 5050))
DEFAULT_VOICE = os.getenv('DEFAULT_VOICE', 'en-US-AndrewNeural')
DEFAULT_RESPONSE_FORMAT = os.getenv('DEFAULT_RESPONSE_FORMAT', 'mp3')
DEFAULT_SPEED = float(os.getenv('DEFAULT_SPEED', 1.0))
# DEFAULT_MODEL = os.getenv('DEFAULT_MODEL', 'tts-1')
# 添加一个简单的 HTML 模板
HOME_TEMPLATE = """
<!DOCTYPE html>
<html lang="zh-CN">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>OpenAI Edge TTS API</title>
<style>
body { font-family: Arial, sans-serif; line-height: 1.6; padding: 20px; max-width: 800px; margin: 0 auto; }
h1 { color: #333; }
pre { background-color: #f4f4f4; padding: 10px; border-radius: 5px; }
</style>
</head>
<body>
<h1>欢迎使用 OpenAI Edge TTS API</h1>
<p>这是一个基于 Edge TTS 的 OpenAI TTS API 替代品。</p>
<h2>API 端点：</h2>
<ul>
<li>TTS 生成：<code>/v1/audio/speech</code> (POST)</li>
<li>列出模型：<code>/v1/models</code> (GET/POST)</li>
<li>列出语音：<code>/v1/voices</code> (GET/POST)</li>
<li>列出所有语音：<code>/v1/voices/all</code> (GET/POST)</li>
</ul>
<h2>使用示例：</h2>
<pre>
curl http://localhost:{{ port }}/v1/audio/speech \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tts-1",
"input": "Hello world!",
"voice": "alloy"
}' \
--output speech.mp3
</pre>
<p>更多信息请参考 API 文档。</p>
</body>
</html>
"""
@app.route('/')
def home():
return render_template_string(HOME_TEMPLATE, port=PORT)
@app.route('/v1/audio/speech', methods=['POST'])
@require_api_key
def text_to_speech():
data = request.json
if not data or 'input' not in data:
return jsonify({"error": "Missing 'input' in request body"}), 400
text = data.get('input')
# model = data.get('model', DEFAULT_MODEL)
voice = data.get('voice', DEFAULT_VOICE)
response_format = data.get('response_format', DEFAULT_RESPONSE_FORMAT)
speed = float(data.get('speed', DEFAULT_SPEED))
mime_type = AUDIO_FORMAT_MIME_TYPES.get(response_format, "audio/mpeg")
# Generate the audio file in the specified format with speed adjustment
output_file_path = generate_speech(text, voice, response_format, speed)
# Return the file with the correct MIME type
return send_file(output_file_path, mimetype=mime_type, as_attachment=True, download_name=f"speech.{response_format}")
@app.route('/v1/models', methods=['GET', 'POST'])
@require_api_key
def list_models():
return jsonify({"data": get_models()})
@app.route('/v1/voices', methods=['GET', 'POST'])
@require_api_key
def list_voices():
specific_language = None
data = request.args if request.method == 'GET' else request.json
if data and ('language' in data or 'locale' in data):
specific_language = data.get('language') if 'language' in data else data.get('locale')
return jsonify({"voices": get_voices(specific_language)})
@app.route('/v1/voices/all', methods=['GET', 'POST'])
@require_api_key
def list_all_voices():
return jsonify({"voices": get_voices('all')})
print(f" Edge TTS (Free Azure TTS) Replacement for OpenAI's TTS API")
print(f" ")
print(f" * Serving OpenAI Edge TTS")
print(f" * Server running on http://localhost:{PORT}")
print(f" * TTS Endpoint: http://localhost:{PORT}/v1/audio/speech")
print(f" ")
if __name__ == '__main__':
http_server = WSGIServer(('0.0.0.0', PORT), app)
http_server.serve_forever()
|