feat: AI回复语音播放功能（Edge TTS）

backend/app.py

@@ -4,7 +4,7 @@ AI Chat App - 后台管理服务
 端口: 19021 (与前端同一端口)
 """
 
-from flask import Flask, jsonify, request, send_from_directory
+from flask import Flask, jsonify, request, send_from_directory, Response
 from flask_cors import CORS
 import os
 import json
@@ -12,6 +12,8 @@ import sqlite3
 from datetime import datetime
 import hashlib
 import base64
+import asyncio
+import edge_tts
 
 app = Flask(__name__, static_folder='../www')
 CORS(app)
@@ -273,6 +275,8 @@ def init_db():
             ('app_description', '提供智能对话、多种智能体服务', '应用简介'),
             ('privacy_policy_url', '', '隐私政策链接'),
             ('user_agreement_url', '', '用户协议链接'),
+            ('tts_provider', 'edge', 'TTS方案'),
+            ('tts_voice', 'zh-CN-XiaoxiaoNeural', 'TTS语音'),
         ]
         for key, value, desc in default_configs:
             cursor.execute('INSERT INTO system_configs (key, value, description) VALUES (?, ?, ?)', (key, value, desc))
@@ -285,6 +289,8 @@ def init_db():
             ('app_description', '提供智能对话、多种智能体服务', '应用简介'),
             ('privacy_policy_url', '', '隐私政策链接'),
             ('user_agreement_url', '', '用户协议链接'),
+            ('tts_provider', 'edge', 'TTS方案'),
+            ('tts_voice', 'zh-CN-XiaoxiaoNeural', 'TTS语音'),
         ]
         for key, value, desc in default_configs:
             cursor.execute('SELECT COUNT(*) FROM system_configs WHERE key=?', (key,))
@@ -1386,12 +1392,62 @@ def get_frontend_config():
             'description': system.get('app_description', '提供智能对话、多种智能体服务'),
             'privacyPolicyUrl': system.get('privacy_policy_url', ''),
             'userAgreementUrl': system.get('user_agreement_url', ''),
+            'ttsProvider': system.get('tts_provider', 'edge'),
+            'ttsVoice': system.get('tts_voice', 'zh-CN-XiaoxiaoNeural'),
         }
     }
     
     return jsonify(config)
 
 
+# ==================== TTS 语音合成 ====================
+
+@app.route('/api/tts', methods=['POST'])
+def generate_tts():
+    """使用 Edge TTS 生成语音"""
+    data = request.json
+    text = data.get('text', '')
+    voice = data.get('voice', 'zh-CN-XiaoxiaoNeural')  # 默认中文女声
+    
+    if not text:
+        return jsonify({'error': '缺少文本内容'}), 400
+    
+    try:
+        # 使用 asyncio 运行 edge_tts
+        async def generate_audio():
+            communicate = edge_tts.Communicate(text, voice)
+            audio_data = b''
+            for chunk in communicate.stream_sync():
+                if chunk['type'] == 'audio':
+                    audio_data += chunk['data']
+            return audio_data
+        
+        audio_data = asyncio.run(generate_audio())
+        
+        # 返回音频数据（MP3格式）
+        return Response(audio_data, mimetype='audio/mpeg')
+    
+    except Exception as e:
+        return jsonify({'error': f'TTS生成失败: {str(e)}'}), 500
+
+
+@app.route('/api/tts/voices', methods=['GET'])
+def get_tts_voices():
+    """获取可用的 TTS 语音列表"""
+    try:
+        voices = asyncio.run(edge_tts.list_voices())
+        # 过滤中文语音
+        chinese_voices = [v for v in voices if v['Locale'].startswith('zh-')]
+        voice_list = [{
+            'name': v['ShortName'],
+            'gender': v['Gender'],
+            'locale': v['Locale']
+        } for v in chinese_voices]
+        return jsonify({'voices': voice_list})
+    except Exception as e:
+        return jsonify({'error': f'获取语音列表失败: {str(e)}'}), 500
+
+
 # ==================== 启动 ====================
 
 if __name__ == '__main__':