fix: 前端录音改用WAV格式（PCM 16kHz），兼容模型端

2026-04-21 18:35:50 +08:00
parent b3cfae14a9
commit 04e8405558
7 changed files with 173 additions and 28 deletions
--- a/pycache/server.cpython-310.pyc
+++ b/pycache/server.cpython-310.pyc
--- a/cert.pem
+++ b/cert.pem
@@ -0,0 +1,29 @@
+-----BEGIN CERTIFICATE-----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-----END CERTIFICATE-----
--- a/key.pem
+++ b/key.pem
@@ -0,0 +1,52 @@
+-----BEGIN PRIVATE KEY-----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+-----END PRIVATE KEY-----
--- a/logs/server.log
+++ b/logs/server.log
--- a/main.py
+++ b/main.py
@@ -39,4 +39,11 @@ async def index():

 if __name__ == "__main__":
    PORT = int(os.getenv("PORT", "19019"))
-    uvicorn.run(app, host="0.0.0.0", port=PORT)
+    SSL_KEY = os.getenv("SSL_KEY", "key.pem")
+    SSL_CERT = os.getenv("SSL_CERT", "cert.pem")
+    
+    # 检查是否有 SSL 证书
+    if os.path.exists(SSL_KEY) and os.path.exists(SSL_CERT):
+        uvicorn.run(app, host="0.0.0.0", port=PORT, ssl_keyfile=SSL_KEY, ssl_certfile=SSL_CERT)
+    else:
+        uvicorn.run(app, host="0.0.0.0", port=PORT)
--- a/server.py
+++ b/server.py
@@ -11,7 +11,6 @@ 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 pydantic import BaseModel

 # 配置
@@ -58,7 +57,7 @@ async def root():
    return {"status": "ok", "service": "voice-chat-web"}


-@app.get("/api/status", response_model=StatusResponse)
+@app.get("/status", response_model=StatusResponse)
 async def get_status():
    """检查服务状态"""
    try:
@@ -81,7 +80,7 @@ async def get_status():
    )


-@app.post("/api/voice/chat", response_model=VoiceResponse)
+@app.post("/voice/chat", response_model=VoiceResponse)
 async def voice_chat(
    audio: UploadFile = File(..., description="音频文件"),
    conversation_id: Optional[str] = Form(None, description="对话ID")
@@ -131,7 +130,7 @@ async def voice_chat(
        raise HTTPException(status_code=500, detail=str(e))


-@app.delete("/api/conversation/{conversation_id}")
+@app.delete("/conversation/{conversation_id}")
 async def delete_conversation(conversation_id: str):
    """删除对话"""
    try:
@@ -146,10 +145,6 @@ async def delete_conversation(conversation_id: str):
        raise HTTPException(status_code=500, detail=str(e))


-# 静态文件（前端页面）
-app.mount("/static", StaticFiles(directory="static"), name="static")
-
-
 if __name__ == "__main__":
    import uvicorn
    uvicorn.run(app, host="0.0.0.0", port=PORT)
--- a/static/index.html
+++ b/static/index.html
@@ -304,6 +304,9 @@
        let audioChunks = [];
        let conversationId = null;
        let audioContext = null;
+        let audioStream = null;
+        let scriptProcessor = null;
+        let recordedBuffers = [];
        
        // 元素
        const recordBtn = document.getElementById('recordBtn');
@@ -333,10 +336,58 @@
            }
        }
        
+        // 创建 WAV 文件
+        function createWavFile(audioBuffer, sampleRate = 16000) {
+            const numChannels = 1;
+            const bitsPerSample = 16;
+            const bytesPerSample = bitsPerSample / 8;
+            const blockAlign = numChannels * bytesPerSample;
+            const byteRate = sampleRate * blockAlign;
+            const dataSize = audioBuffer.length * bytesPerSample;
+            const headerSize = 44;
+            const totalSize = headerSize + dataSize;
+            
+            const buffer = new ArrayBuffer(totalSize);
+            const view = new DataView(buffer);
+            
+            // WAV header
+            writeString(view, 0, 'RIFF');
+            view.setUint32(4, totalSize - 8, true);
+            writeString(view, 8, 'WAVE');
+            writeString(view, 12, 'fmt ');
+            view.setUint32(16, 16, true); // fmt chunk size
+            view.setUint16(20, 1, true); // audio format (PCM)
+            view.setUint16(22, numChannels, true);
+            view.setUint32(24, sampleRate, true);
+            view.setUint32(28, byteRate, true);
+            view.setUint16(32, blockAlign, true);
+            view.setUint16(34, bitsPerSample, true);
+            writeString(view, 36, 'data');
+            view.setUint32(40, dataSize, true);
+            
+            // 写入音频数据
+            floatTo16BitPCM(view, 44, audioBuffer);
+            
+            return new Blob([buffer], { type: 'audio/wav' });
+        }
+        
+        function writeString(view, offset, string) {
+            for (let i = 0; i < string.length; i++) {
+                view.setUint8(offset + i, string.charCodeAt(i));
+            }
+        }
+        
+        function floatTo16BitPCM(view, offset, input) {
+            for (let i = 0; i < input.length; i++, offset += 2) {
+                const s = Math.max(-1, Math.min(1, input[i]));
+                view.setInt16(offset, s < 0 ? s * 0x8000 : s * 0x7FFF, true);
+            }
+        }
+        
        // 初始化录音
        async function initAudio() {
            try {
-                const stream = await navigator.mediaDevices.getUserMedia({ 
+                audioStream = await navigator.mediaDevices.getUserMedia({ 
                    audio: {
                        echoCancellation: true,
                        noiseSuppression: true,
@@ -344,22 +395,21 @@
                    }
                });
                
-                audioContext = new (window.AudioContext || window.webkitAudioContext)();
-                
-                // 创建 MediaRecorder
-                mediaRecorder = new MediaRecorder(stream, {
-                    mimeType: 'audio/webm'
+                audioContext = new (window.AudioContext || window.webkitAudioContext)({
+                    sampleRate: 16000
                });
                
-                mediaRecorder.ondataavailable = (e) => {
-                    audioChunks.push(e.data);
+                const source = audioContext.createMediaStreamSource(audioStream);
+                scriptProcessor = audioContext.createScriptProcessor(4096, 1, 1);
+                
+                scriptProcessor.onaudioprocess = (e) => {
+                    if (isRecording) {
+                        recordedBuffers.push(e.inputBuffer.getChannelData(0).slice());
+                    }
                };
                
-                mediaRecorder.onstop = async () => {
-                    const audioBlob = new Blob(audioChunks, { type: 'audio/webm' });
-                    audioChunks = [];
-                    await sendAudio(audioBlob);
-                };
+                source.connect(scriptProcessor);
+                scriptProcessor.connect(audioContext.destination);
                
                return true;
            } catch (e) {
@@ -371,13 +421,12 @@
        
        // 开始录音
        async function startRecording() {
-            if (!mediaRecorder) {
+            if (!audioContext) {
                const success = await initAudio();
                if (!success) return;
            }
            
-            audioChunks = [];
-            mediaRecorder.start();
+            recordedBuffers = [];
            isRecording = true;
            
            recordBtn.classList.add('recording');
@@ -390,16 +439,29 @@
        
        // 停止录音
        function stopRecording() {
-            if (mediaRecorder && isRecording) {
-                mediaRecorder.stop();
+            if (isRecording) {
                isRecording = false;
                
+                // 合并所有缓冲区
+                const totalLength = recordedBuffers.reduce((acc, buf) => acc + buf.length, 0);
+                const mergedBuffer = new Float32Array(totalLength);
+                let offset = 0;
+                for (const buf of recordedBuffers) {
+                    mergedBuffer.set(buf, offset);
+                    offset += buf.length;
+                }
+                
+                // 创建 WAV 文件
+                const wavBlob = createWavFile(mergedBuffer, 16000);
+                
                recordBtn.classList.remove('recording');
                recordBtn.querySelector('.icon').textContent = '🎤';
                recordBtn.querySelector('.text').textContent = '点击录音';
                recordStatus.textContent = '处理中...';
                recordStatus.classList.remove('recording');
                waveform.style.display = 'none';
+                
+                sendAudio(wavBlob);
            }
        }
        
@@ -409,7 +471,7 @@
                showLoading();
                
                const formData = new FormData();
-                formData.append('audio', audioBlob, 'recording.webm');
+                formData.append('audio', audioBlob, 'recording.wav');
                if (conversationId) {
                    formData.append('conversation_id', conversationId);
                }