Update app.py

app.py

@@ -1,9 +1,12 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, UploadFile, File
 from fastapi.middleware.cors import CORSMiddleware
+from fastapi import HTTPException
 from pydantic import BaseModel
 import openai
 from dotenv import load_dotenv
 import os
+from deepgram import DeepgramClient, PrerecordedOptions
+
 
 # Load environment variables from .env file
 load_dotenv()
@@ -14,6 +17,10 @@ openai.api_base = "https://amplifai-openai.openai.azure.com/"
 openai.api_version = "2023-07-01-preview"
 openai.api_key = os.getenv("OPENAI_API_KEY")
 
+DEEPGRAM_API_KEY = os.getenv("DEEPGRAM_API_KEY")
+if not DEEPGRAM_API_KEY:
+    raise Exception("Deepgram API key not found in environment variables")
+
 app = FastAPI()
 
 class Prompt(BaseModel):
@@ -178,6 +185,25 @@ def custom_qa_automation(text: str, custom_question: str):
 
     return GenerateResponse(text=formatted_answer)
 
+# Transcription function
+def transcription(file):
+    try:
+        deepgram = DeepgramClient(DEEPGRAM_API_KEY)
+        if isinstance(file, str):  # File from folder
+            with open(file, "rb") as f:
+                buffer_data = f.read()
+        else:  # Uploaded file
+            buffer_data = file.file.read()
+
+        payload = {"buffer": buffer_data}
+        options = PrerecordedOptions(model="nova-2", smart_format=True, diarize=True, redact='ssn')
+        response = deepgram.listen.prerecorded.v("1").transcribe_file(payload, options)
+        return response
+    except Exception as e:
+        print(f"Exception: {e}")
+        return None
+
+ALLOWED_EXTENSIONS = {".mp3", ".wav", ".wma"}
 
 app.add_middleware(
     CORSMiddleware,
@@ -206,3 +232,17 @@ def inference(input_prompt: Prompt):
 @app.post("/api/custom-qa", summary="Generate text from prompt", tags=["Generate"], response_model=GenerateResponse)
 def inference(input_prompt: Prompt, question: Prompt):
     return custom_qa_automation(text=input_prompt.text, custom_question=question.text)
+
+
+@app.post("/api/transcribe-audio", summary="Transcribe audio file", tags=["Transcription"])
+async def transcribe_audio_route(file: UploadFile = File(...)):
+    # Check if the file extension is allowed
+    file_extension = os.path.splitext(file.filename)[1].lower()
+    if file_extension not in ALLOWED_EXTENSIONS:
+        raise HTTPException(status_code=400, detail=f"File format not supported. Allowed formats: {', '.join(ALLOWED_EXTENSIONS)}")
+
+    transcription_result = transcription(file)
+    if transcription_result:
+        return transcription_result
+    else:
+        return {"error": "Transcription failed"}