add audio api

app.py

@@ -1,10 +1,12 @@
-from fastapi import FastAPI, HTTPException
+from fastapi import FastAPI, HTTPException, UploadFile
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import JSONResponse
 from utils.validators import ChatRequest, ChatResponse
 from utils.logger import log
 from modules.travel_assistant import TravelAssistant
 import traceback
+import tempfile
+import shutil
 
 # --- FastAPI 应用设置 ---
 app = FastAPI(
@@ -146,6 +148,57 @@ async def reset_session(session_id: str):
             detail="Failed to reset session"
         )
     
+@app.post("/api/transcribe-audio")
+async def transcribe_audio_endpoint(file: UploadFile = File(...)):
+    """
+    接收音频文件，进行语音转文本，并返回转录结果。
+    """
+    # 1. 检查核心服务是否就绪
+    if not SERVICE_READY or not assistant:
+        raise HTTPException(
+            status_code=503,
+            detail="Service Unavailable: Backend assistant failed to initialize."
+        )
+
+    # 2. 检查上传的是否是音频文件 (基础检查)
+    if not file.content_type.startswith("audio/"):
+        raise HTTPException(
+            status_code=400,
+            detail=f"Invalid file type: {file.content_type}. Please upload an audio file."
+        )
+
+    tmp_path = None
+    try:
+        # 3. 创建一个带正确后缀的临时文件，以便模型能识别
+        #    例如，如果上传 a.wav, 临时文件也会是 xxx.wav
+        suffix = os.path.splitext(file.filename)[1]
+        with tempfile.NamedTemporaryFile(delete=False, suffix=suffix) as tmp:
+            # 将上传的文件内容写入临时文件
+            shutil.copyfileobj(file.file, tmp)
+            tmp_path = tmp.name
+        
+        log.info(f"音频文件已临时保存到: {tmp_path}")
+
+        # 4. 调用 TravelAssistant 中的转录方法
+        transcribed_text = assistant.transcribe_audio(audio_path=tmp_path)
+        
+        log.info(f"音频转录成功，内容: {transcribed_text[:50]}...")
+        
+        # 5. 将转录文本作为 JSON 返回
+        return {"transcription": transcribed_text}
+
+    except Exception as e:
+        log.error(f"❌ Audio transcription error: {e}", exc_info=True)
+        raise HTTPException(
+            status_code=500,
+            detail="Internal Server Error: Failed to transcribe audio."
+        )
+    finally:
+        # 6. 无论成功与否，都确保清理临时文件
+        if tmp_path and os.path.exists(tmp_path):
+            os.remove(tmp_path)
+            log.info(f"临时文件已清理: {tmp_path}")
+
 @app.get("/api/debug/sessions")
 async def debug_sessions():
     """调试：查看所有会话状态"""
@@ -198,6 +251,8 @@ async def cleanup_sessions(max_age_hours: int = 24):
     except Exception as e:
         log.error(f"❌ Cleanup error: {e}")
         raise HTTPException(status_code=500, detail="Failed to cleanup sessions")
+    
+
 
 # --- 全局异常处理 ---
 @app.exception_handler(Exception)