Update app.py

app.py

@@ -1,4 +1,6 @@
-from fastapi import FastAPI, HTTPException
+import os
+from fastapi import FastAPI, HTTPException, File, UploadFile, Depends, Security
+from fastapi.security.api_key import APIKeyHeader, APIKey
 from fastapi.responses import JSONResponse
 from pydantic import BaseModel
 import numpy as np
@@ -13,7 +15,6 @@ from pydub import AudioSegment
 from moviepy.editor import VideoFileClip
 import traceback
 from logging.handlers import RotatingFileHandler
-import os
 import boto3
 from botocore.exceptions import NoCredentialsError
 import time
@@ -44,6 +45,10 @@ S3_REGION = os.environ.get("S3_REGION")
 S3_ACCESS_KEY_ID = os.environ.get("AWS_ACCESS_KEY_ID")
 S3_SECRET_ACCESS_KEY = os.environ.get("AWS_SECRET_ACCESS_KEY")
 
+# API Key Configuration
+API_KEY = os.environ.get("API_KEY")
+api_key_header = APIKeyHeader(name="X-API-Key", auto_error=False)
+
 # Initialize S3 client
 s3_client = boto3.client(
     's3',
@@ -62,6 +67,11 @@ class TTSRequest(BaseModel):
     language: str
     speed: float
 
+async def get_api_key(api_key_header: str = Security(api_key_header)):
+    if api_key_header == API_KEY:
+        return api_key_header
+    raise HTTPException(status_code=403, detail="Could not validate credentials")
+
 def extract_audio_from_file(input_bytes):
     with tempfile.NamedTemporaryFile(delete=False, suffix='.tmp') as temp_file:
         temp_file.write(input_bytes)
@@ -114,7 +124,7 @@ def extract_audio_from_file(input_bytes):
         os.unlink(temp_file_path)
 
 @app.post("/transcribe")
-async def transcribe_audio(request: AudioRequest):
+async def transcribe_audio(request: AudioRequest, api_key: APIKey = Depends(get_api_key)):
     start_time = time.time()
     try:
         input_bytes = base64.b64decode(request.audio)
@@ -142,8 +152,37 @@ async def transcribe_audio(request: AudioRequest):
             content={"message": "An error occurred during transcription", "details": error_details, "processing_time_seconds": processing_time}
         )
 
+@app.post("/transcribe_file")
+async def transcribe_audio_file(file: UploadFile = File(...), language: str = "", api_key: APIKey = Depends(get_api_key)):
+    start_time = time.time()
+    try:
+        contents = await file.read()
+        audio_array, sample_rate = extract_audio_from_file(contents)
+
+        # Ensure audio_array is float32
+        audio_array = audio_array.astype(np.float32)
+
+        # Resample if necessary
+        if sample_rate != ASR_SAMPLING_RATE:
+            audio_array = librosa.resample(audio_array, orig_sr=sample_rate, target_sr=ASR_SAMPLING_RATE)
+
+        result = transcribe(audio_array, language)
+        processing_time = time.time() - start_time
+        return JSONResponse(content={"transcription": result, "processing_time_seconds": processing_time})
+    except Exception as e:
+        logger.error(f"Error in transcribe_audio_file: {str(e)}", exc_info=True)
+        error_details = {
+            "error": str(e),
+            "traceback": traceback.format_exc()
+        }
+        processing_time = time.time() - start_time
+        return JSONResponse(
+            status_code=500,
+            content={"message": "An error occurred during transcription", "details": error_details, "processing_time_seconds": processing_time}
+        )
+
 @app.post("/synthesize")
-async def synthesize_speech(request: TTSRequest):
+async def synthesize_speech(request: TTSRequest, api_key: APIKey = Depends(get_api_key)):
     start_time = time.time()
     logger.info(f"Synthesize request received: text='{request.text}', language='{request.language}', speed={request.speed}")
     try:
@@ -241,7 +280,7 @@ async def synthesize_speech(request: TTSRequest):
         logger.info("Synthesize request completed")
 
 @app.post("/identify")
-async def identify_language(request: AudioRequest):
+async def identify_language(request: AudioRequest, api_key: APIKey = Depends(get_api_key)):
     start_time = time.time()
     try:
         input_bytes = base64.b64decode(request.audio)
@@ -261,8 +300,29 @@ async def identify_language(request: AudioRequest):
             content={"message": "An error occurred during language identification", "details": error_details, "processing_time_seconds": processing_time}
         )
 
+@app.post("/identify_file")
+async def identify_language_file(file: UploadFile = File(...), api_key: APIKey = Depends(get_api_key)):
+    start_time = time.time()
+    try:
+        contents = await file.read()
+        audio_array, sample_rate = extract_audio_from_file(contents)
+        result = identify(audio_array)
+        processing_time = time.time() - start_time
+        return JSONResponse(content={"language_identification": result, "processing_time_seconds": processing_time})
+    except Exception as e:
+        logger.error(f"Error in identify_language_file: {str(e)}", exc_info=True)
+        error_details = {
+            "error": str(e),
+            "traceback": traceback.format_exc()
+        }
+        processing_time = time.time() - start_time
+        return JSONResponse(
+            status_code=500,
+            content={"message": "An error occurred during language identification", "details": error_details, "processing_time_seconds": processing_time}
+        )
+
 @app.get("/asr_languages")
-async def get_asr_languages():
+async def get_asr_languages(api_key: APIKey = Depends(get_api_key)):
     start_time = time.time()
     try:
         processing_time = time.time() - start_time
@@ -280,7 +340,7 @@ async def get_asr_languages():
         )
 
 @app.get("/tts_languages")
-async def get_tts_languages():
+async def get_tts_languages(api_key: APIKey = Depends(get_api_key)):
     start_time = time.time()
     try:
         processing_time = time.time() - start_time