feat: 添加自动播放开关和音量调节功能

main.py

@@ -33,10 +33,16 @@ app.mount("/static", StaticFiles(directory="static"), name="static")
 
 @app.get("/")
 async def index():
-    """主页"""
+    """主页（原版）"""
     return FileResponse("static/index.html")
 
 
+@app.get("/tts")
+async def tts_page():
+    """TTS版本页面"""
+    return FileResponse("static/tts.html")
+
+
 if __name__ == "__main__":
     PORT = int(os.getenv("PORT", "19019"))
     SSL_KEY = os.getenv("SSL_KEY", "key.pem")

requirements.txt

@@ -1,4 +1,6 @@
 fastapi==0.110.0
 uvicorn==0.27.1
 python-multipart==0.0.9
-aiohttp==3.9.3
+aiohttp==3.9.3
+edge-tts==6.1.9
+requests==2.31.0

server.py

@@ -11,8 +11,13 @@ from datetime import datetime
 import aiohttp
 from fastapi import FastAPI, UploadFile, File, HTTPException, Form
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi.staticfiles import StaticFiles
+from fastapi.responses import FileResponse
 from pydantic import BaseModel
 
+# 导入 TTS 服务
+from tts_service import tts_manager, AUDIO_DIR
+
 # 配置
 MODEL_SERVICE_URL = os.getenv("MODEL_SERVICE_URL", "http://localhost:19018")
 PORT = int(os.getenv("PORT", "19019"))
@@ -130,6 +135,47 @@ async def voice_chat(
         raise HTTPException(status_code=500, detail=str(e))
 
 
+@app.post("/voice/text", response_model=VoiceResponse)
+async def text_chat(
+    text: str = Form(..., description="文本消息"),
+    conversation_id: Optional[str] = Form(None, description="对话ID")
+):
+    """
+    文字聊天接口
+    转发到模型服务
+    """
+    try:
+        async with aiohttp.ClientSession() as session:
+            form = aiohttp.FormData()
+            form.add_field('text', text)
+            if conversation_id:
+                form.add_field('conversation_id', conversation_id)
+            
+            async with session.post(
+                f"{MODEL_SERVICE_URL}/api/voice/text",
+                data=form,
+                timeout=aiohttp.ClientTimeout(total=120)
+            ) as resp:
+                if resp.status != 200:
+                    error_text = await resp.text()
+                    logger.error(f"Model service error: {error_text}")
+                    raise HTTPException(status_code=resp.status, detail=error_text)
+                
+                data = await resp.json()
+                return VoiceResponse(
+                    reply=data["reply"],
+                    conversation_id=data["conversation_id"],
+                    timestamp=data.get("timestamp", datetime.now().isoformat())
+                )
+                
+    except aiohttp.ClientError as e:
+        logger.error(f"Connection error: {e}")
+        raise HTTPException(status_code=503, detail="模型服务连接失败")
+    except Exception as e:
+        logger.error(f"Text chat error: {e}", exc_info=True)
+        raise HTTPException(status_code=500, detail=str(e))
+
+
 @app.delete("/conversation/{conversation_id}")
 async def delete_conversation(conversation_id: str):
     """删除对话"""
@@ -145,6 +191,70 @@ async def delete_conversation(conversation_id: str):
         raise HTTPException(status_code=500, detail=str(e))
 
 
+# ========== TTS 相关接口 ==========
+
+class TTSSettings(BaseModel):
+    """TTS 设置"""
+    provider: str = "none"
+    voice: Optional[str] = None
+
+
+class TTSResponse(BaseModel):
+    """TTS 响应"""
+    audio_url: Optional[str]
+    provider: str
+
+
+@app.get("/tts/providers")
+async def get_tts_providers():
+    """获取可用的 TTS 方案列表"""
+    providers = tts_manager.list_providers()
+    voices = tts_manager.get_edge_voices()
+    return {
+        "providers": providers,
+        "voices": voices,
+        "current": tts_manager.current_provider
+    }
+
+
+@app.post("/tts/settings")
+async def set_tts_settings(settings: TTSSettings):
+    """设置 TTS 方案"""
+    tts_manager.set_provider(settings.provider)
+    
+    # 设置音色（仅 Edge TTS）
+    if settings.provider == "edge" and settings.voice:
+        provider = tts_manager.get_provider("edge")
+        if hasattr(provider, 'set_voice'):
+            provider.set_voice(settings.voice)
+    
+    return {
+        "provider": settings.provider,
+        "voice": settings.voice
+    }
+
+
+@app.post("/tts/synthesize")
+async def synthesize_tts(text: str = Form(...), provider: Optional[str] = Form(None)):
+    """
+    合成语音
+    返回音频文件 URL
+    """
+    try:
+        audio_url = await tts_manager.synthesize(text, provider)
+        return TTSResponse(
+            audio_url=audio_url,
+            provider=provider or tts_manager.current_provider
+        )
+    except Exception as e:
+        logger.error(f"TTS synthesis error: {e}")
+        raise HTTPException(status_code=500, detail=str(e))
+
+
+# 挂载音频文件目录
+app.mount("/audio", StaticFiles(directory=AUDIO_DIR), name="audio")
+
+
 if __name__ == "__main__":
     import uvicorn
     uvicorn.run(app, host="0.0.0.0", port=PORT)

static/index.html

@@ -127,6 +127,50 @@
             font-weight: bold;
         }
         
+        .text-section {
+            margin: 20px 0;
+        }
+        
+        .text-input-wrapper {
+            display: flex;
+            gap: 10px;
+        }
+        
+        .text-input {
+            flex: 1;
+            padding: 12px 15px;
+            border: 2px solid #eee;
+            border-radius: 10px;
+            font-size: 15px;
+            outline: none;
+            transition: border-color 0.2s;
+        }
+        
+        .text-input:focus {
+            border-color: #667eea;
+        }
+        
+        .send-text-btn {
+            padding: 12px 20px;
+            border: none;
+            border-radius: 10px;
+            background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+            color: white;
+            font-size: 15px;
+            cursor: pointer;
+            transition: all 0.2s;
+        }
+        
+        .send-text-btn:hover {
+            transform: scale(1.05);
+        }
+        
+        .send-text-btn:disabled {
+            opacity: 0.5;
+            cursor: not-allowed;
+            transform: none;
+        }
+        
         .waveform {
             display: flex;
             justify-content: center;
@@ -196,6 +240,40 @@
             line-height: 1.5;
         }
         
+        .audio-content {
+            display: flex;
+            align-items: center;
+        }
+        
+        .play-btn {
+            display: inline-flex;
+            align-items: center;
+            gap: 8px;
+            padding: 8px 15px;
+            border-radius: 20px;
+            border: none;
+            background: rgba(255,255,255,0.2);
+            cursor: pointer;
+            transition: all 0.2s;
+            font-size: 14px;
+        }
+        
+        .play-btn:hover {
+            background: rgba(255,255,255,0.3);
+        }
+        
+        .play-btn.playing {
+            background: rgba(255,255,255,0.4);
+        }
+        
+        .play-icon {
+            font-size: 16px;
+        }
+        
+        .duration {
+            color: rgba(255,255,255,0.8);
+        }
+        
         .loading {
             display: flex;
             justify-content: center;
@@ -285,6 +363,13 @@
             </div>
         </div>
         
+        <div class="text-section">
+            <div class="text-input-wrapper">
+                <input type="text" id="textInput" placeholder="输入文字消息..." class="text-input">
+                <button id="sendTextBtn" class="send-text-btn">发送</button>
+            </div>
+        </div>
+        
         <div class="chat-section" id="chatSection">
             <div class="hint">开始你的第一次语音对话吧！</div>
         </div>
@@ -316,6 +401,46 @@
         const clearBtn = document.getElementById('clearBtn');
         const statusDot = document.getElementById('statusDot');
         const statusText = document.getElementById('statusText');
+        const textInput = document.getElementById('textInput');
+        const sendTextBtn = document.getElementById('sendTextBtn');
+        
+        // 发送文字消息
+        async function sendText(text) {
+            if (!text.trim()) return;
+            
+            try {
+                showLoading();
+                
+                const formData = new FormData();
+                formData.append('text', text);
+                if (conversationId) {
+                    formData.append('conversation_id', conversationId);
+                }
+                
+                const resp = await fetch(`${API_URL}/voice/text`, {
+                    method: 'POST',
+                    body: formData
+                });
+                
+                if (!resp.ok) {
+                    const error = await resp.text();
+                    throw new Error(error);
+                }
+                
+                const data = await resp.json();
+                conversationId = data.conversation_id;
+                
+                // 显示消息
+                addMessage('user', text);
+                addMessage('assistant', data.reply);
+                
+                textInput.value = '';
+                
+            } catch (e) {
+                console.error('发送失败:', e);
+                showError('发送失败: ' + e.message);
+            }
+        }
         
         // 检查服务状态
         async function checkStatus() {
@@ -470,6 +595,9 @@
             try {
                 showLoading();
                 
+                // 计算音频时长
+                const duration = Math.round(recordedBuffers.reduce((acc, buf) => acc + buf.length, 0) / 16000);
+                
                 const formData = new FormData();
                 formData.append('audio', audioBlob, 'recording.wav');
                 if (conversationId) {
@@ -489,8 +617,8 @@
                 const data = await resp.json();
                 conversationId = data.conversation_id;
                 
-                // 显示消息
-                addMessage('user', '🎵 语音消息');
+                // 显示消息（带音频播放）
+                addMessage('user', audioBlob, duration);
                 addMessage('assistant', data.reply);
                 
                 recordStatus.textContent = '点击按钮开始录音';
@@ -503,7 +631,7 @@
         }
         
         // 添加消息
-        function addMessage(role, content) {
+        function addMessage(role, content, audioDuration = null) {
             // 移除提示
             const hint = chatSection.querySelector('.hint');
             if (hint) hint.remove();
@@ -514,16 +642,50 @@
             
             const msg = document.createElement('div');
             msg.className = `message ${role}`;
-            msg.innerHTML = `
-                <div class="role">${role === 'user' ? '我' : 'AI'}</div>
-                <div class="content">${content}</div>
-            `;
+            
+            // 用户消息可能是音频
+            if (role === 'user' && content instanceof Blob) {
+                const audioUrl = URL.createObjectURL(content);
+                const durationText = audioDuration ? `${audioDuration}s` : '';
+                msg.innerHTML = `
+                    <div class="role">我</div>
+                    <div class="content audio-content">
+                        <button class="play-btn" onclick="playAudio('${audioUrl}', this)">
+                            <span class="play-icon">▶️</span>
+                            <span class="duration">${durationText}</span>
+                        </button>
+                    </div>
+                `;
+            } else {
+                msg.innerHTML = `
+                    <div class="role">${role === 'user' ? '我' : 'AI'}</div>
+                    <div class="content">${content}</div>
+                `;
+            }
             chatSection.appendChild(msg);
             
             // 滚动到底部
             chatSection.scrollTop = chatSection.scrollHeight;
         }
         
+        // 播放音频
+        function playAudio(audioUrl, btn) {
+            const audio = new Audio(audioUrl);
+            const icon = btn.querySelector('.play-icon');
+            
+            audio.onplay = () => {
+                icon.textContent = '🔊';
+                btn.classList.add('playing');
+            };
+            
+            audio.onended = () => {
+                icon.textContent = '▶️';
+                btn.classList.remove('playing');
+            };
+            
+            audio.play();
+        }
+        
         // 显示加载
         function showLoading() {
             const hint = chatSection.querySelector('.hint');
@@ -579,6 +741,17 @@
         
         clearBtn.addEventListener('click', clearChat);
         
+        // 文字输入事件
+        sendTextBtn.addEventListener('click', () => {
+            sendText(textInput.value);
+        });
+        
+        textInput.addEventListener('keypress', (e) => {
+            if (e.key === 'Enter') {
+                sendText(textInput.value);
+            }
+        });
+        
         // 初始化
         checkStatus();
         setInterval(checkStatus, 10000); // 每10秒检查状态

tts_service.py

@@ -0,0 +1,250 @@
+"""
+TTS 语音合成模块
+支持多种 TTS 方案
+"""
+
+import os
+import uuid
+import logging
+import asyncio
+from abc import ABC, abstractmethod
+from typing import Optional, Tuple
+from datetime import datetime
+
+# 配置
+AUDIO_DIR = os.getenv("AUDIO_DIR", "audio_cache")
+os.makedirs(AUDIO_DIR, exist_ok=True)
+
+logger = logging.getLogger(__name__)
+
+
+class TTSProvider(ABC):
+    """TTS 提供者抽象类"""
+    
+    @abstractmethod
+    async def synthesize(self, text: str) -> Tuple[str, str]:
+        """
+        合成语音
+        返回: (音频文件路径, 音频URL路径)
+        """
+        pass
+    
+    @abstractmethod
+    def get_name(self) -> str:
+        """获取提供者名称"""
+        pass
+    
+    @abstractmethod
+    def is_available(self) -> bool:
+        """检查是否可用"""
+        pass
+
+
+class EdgeTTSProvider(TTSProvider):
+    """Edge TTS 提供者（微软免费TTS）"""
+    
+    # 可用音色
+    VOICES = {
+        "zh-CN-XiaoxiaoNeural": "晓晓（女）",
+        "zh-CN-YunxiNeural": "云希（男）",
+        "zh-CN-YunyangNeural": "云扬（男）",
+        "zh-CN-XiaochenNeural": "晓晨（女）",
+        "zh-CN-XiaohanNeural": "晓涵（女）",
+        "zh-CN-XiaomengNeural": "晓梦（女）",
+        "zh-CN-XiaomoNeural": "晓墨（女）",
+        "zh-CN-XiaoruiNeural": "晓睿（女）",
+        "zh-CN-XiaoshuangNeural": "晓双（女）",
+        "zh-CN-XiaoxuanNeural": "晓萱（女）",
+        "zh-CN-XiaoyanNeural": "晓颜（女）",
+        "zh-CN-XiaoyouNeural": "晓悠（女）",
+    }
+    
+    DEFAULT_VOICE = "zh-CN-XiaoxiaoNeural"
+    
+    def __init__(self, voice: Optional[str] = None):
+        self.voice = voice or self.DEFAULT_VOICE
+        self._available = None
+    
+    async def synthesize(self, text: str) -> Tuple[str, str]:
+        """使用 Edge TTS 合成语音"""
+        import edge_tts
+        
+        # 生成唯一文件名
+        filename = f"{uuid.uuid4().hex}.mp3"
+        filepath = os.path.join(AUDIO_DIR, filename)
+        
+        # 合成语音
+        communicate = edge_tts.Communicate(text, self.voice)
+        await communicate.save(filepath)
+        
+        # 返回路径
+        audio_url = f"/audio/{filename}"
+        return filepath, audio_url
+    
+    def get_name(self) -> str:
+        return "Edge TTS"
+    
+    def get_voice_name(self) -> str:
+        """获取当前音色名称"""
+        return self.VOICES.get(self.voice, self.voice)
+    
+    def is_available(self) -> bool:
+        """检查 Edge TTS 是否可用"""
+        if self._available is None:
+            try:
+                import edge_tts
+                self._available = True
+            except ImportError:
+                logger.warning("edge-tts not installed")
+                self._available = False
+        return self._available
+    
+    def set_voice(self, voice: str):
+        """设置音色"""
+        if voice in self.VOICES:
+            self.voice = voice
+        else:
+            logger.warning(f"Unknown voice: {voice}, using default")
+
+
+class ChatTTSProvider(TTSProvider):
+    """ChatTTS 提供者（本地部署）"""
+    
+    # ChatTTS 服务地址
+    CHATTTS_URL = os.getenv("CHATTTS_URL", "http://192.168.2.5:12002")
+    
+    def __init__(self):
+        self._available = None
+    
+    async def synthesize(self, text: str) -> Tuple[str, str]:
+        """使用 ChatTTS 合成语音"""
+        import aiohttp
+        
+        async with aiohttp.ClientSession() as session:
+            form = aiohttp.FormData()
+            form.add_field('text', text)
+            
+            async with session.post(
+                f"{self.CHATTTS_URL}/synthesize",
+                data=form,
+                timeout=aiohttp.ClientTimeout(total=60)
+            ) as resp:
+                if resp.status != 200:
+                    error = await resp.text()
+                    raise Exception(f"ChatTTS error: {error}")
+                
+                data = await resp.json()
+                # ChatTTS 返回的 URL 是相对路径，需要拼接
+                audio_url = f"{self.CHATTTS_URL}{data['audio_url']}"
+                return None, audio_url
+    
+    def get_name(self) -> str:
+        return "ChatTTS"
+    
+    def is_available(self) -> bool:
+        """检查 ChatTTS 是否可用"""
+        if self._available is None:
+            try:
+                import requests
+                resp = requests.get(f"{self.CHATTTS_URL}/health", timeout=5)
+                if resp.status_code == 200:
+                    data = resp.json()
+                    self._available = data.get("status") == "ok"
+                else:
+                    self._available = False
+            except Exception as e:
+                logger.warning(f"ChatTTS check failed: {e}")
+                self._available = False
+        return self._available
+    
+    def set_url(self, url: str):
+        """设置服务地址"""
+        self.CHATTTS_URL = url
+        self._available = None  # 重新检测
+
+
+class NoTTSProvider(TTSProvider):
+    """不使用 TTS"""
+    
+    async def synthesize(self, text: str) -> Tuple[str, str]:
+        return None, None
+    
+    def get_name(self) -> str:
+        return "无 TTS"
+    
+    def is_available(self) -> bool:
+        return True
+
+
+# TTS 管理器
+class TTSManager:
+    """TTS 方案管理"""
+    
+    PROVIDERS = {
+        "edge": EdgeTTSProvider,
+        "chattts": ChatTTSProvider,
+        "none": NoTTSProvider,
+    }
+    
+    def __init__(self, default_provider: str = "none"):
+        self.current_provider = default_provider
+        self._providers = {}
+        
+        # 初始化 Edge TTS（如果可用）
+        edge_provider = EdgeTTSProvider()
+        if edge_provider.is_available():
+            self._providers["edge"] = edge_provider
+        
+        # 初始化 ChatTTS（预留）
+        self._providers["chattts"] = ChatTTSProvider()
+        
+        # 无 TTS
+        self._providers["none"] = NoTTSProvider()
+    
+    def get_provider(self, provider_name: Optional[str] = None) -> TTSProvider:
+        """获取 TTS 提供者"""
+        name = provider_name or self.current_provider
+        return self._providers.get(name, self._providers["none"])
+    
+    def set_provider(self, provider_name: str):
+        """设置当前 TTS 方案"""
+        if provider_name in self._providers:
+            self.current_provider = provider_name
+        else:
+            logger.warning(f"Unknown provider: {provider_name}")
+    
+    def list_providers(self) -> list:
+        """列出所有可用方案"""
+        return [
+            {
+                "name": name,
+                "display_name": provider.get_name(),
+                "available": provider.is_available()
+            }
+            for name, provider in self._providers.items()
+        ]
+    
+    def get_edge_voices(self) -> dict:
+        """获取 Edge TTS 可用音色"""
+        return EdgeTTSProvider.VOICES
+    
+    async def synthesize(self, text: str, provider_name: Optional[str] = None) -> Optional[str]:
+        """
+        合成语音
+        返回音频URL
+        """
+        provider = self.get_provider(provider_name)
+        if not provider.is_available():
+            logger.warning(f"Provider {provider.get_name()} not available")
+            return None
+        
+        try:
+            _, audio_url = await provider.synthesize(text)
+            return audio_url
+        except Exception as e:
+            logger.error(f"TTS synthesis failed: {e}")
+            return None
+
+
+# 全局 TTS 管理器
+tts_manager = TTSManager()