Upload 4 files

Dockerfile

@@ -0,0 +1,20 @@
+# Use an official Python runtime as the base image
+FROM python:3.9-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the requirements file into the container
+COPY requirements.txt .
+
+# Install the required packages
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application code into the container
+COPY . .
+
+# Expose the port that FastAPI will run on
+EXPOSE 7860
+
+# Command to run the FastAPI application
+CMD ["uvicorn", "SERVER_fastAPI:app", "--host", "0.0.0.0", "--port", "7860"]

elevenlabs.py

@@ -0,0 +1,28 @@
+import requests
+
+def generate_speech(model, voice, input_text):
+    url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice}?allow_unauthenticated=1"
+    headers = {
+        "Content-Type": "application/json"
+    }
+    data = {
+        "text": input_text,
+        "model_id": model,
+    }
+
+    response = requests.post(url, json=data, headers=headers)
+    
+    if response.status_code == 200:
+        return response.content
+    else:
+        print(f"Failed to generate speech: {response.status_code}, {response.text}")
+        return [response.status_code, response.text]
+
+if __name__ == "__main__":
+    text = """हमारा भारत एक विविधताओं से भरा देश है।
+              यहाँ कई भाषाएँ, संस्कृतियाँ और परंपराएँ एक साथ फलती-फूलती हैं।
+              प्रकृति ने भी इस देश को अपार सुंदरता से सजाया है।
+              पहाड़, नदियाँ, समुद्र और हरे-भरे जंगल, सभी इसकी शोभा बढ़ाते हैं।"""
+    model = "eleven_multilingual_v2"
+    voice = "XB0fDUnXU5powFXDhCwa"
+    print(generate_speech(model, voice, text))

requirements.txt

@@ -0,0 +1,5 @@
+fastapi==0.110.2
+Flask==3.0.3
+Requests==2.31.0
+uvicorn==0.29.0
+openai==1.51.0

server_fastAPI.py

@@ -0,0 +1,42 @@
+from fastapi import FastAPI, HTTPException, Response
+from pydantic import BaseModel
+from elevenlabs import generate_speech
+
+app = FastAPI()
+
+class SpeechRequest(BaseModel):
+    model: str
+    input: str
+    voice: str
+
+@app.post("/v1/audio/speech")
+async def create_speech(request: SpeechRequest):
+    try:
+        # Map the OpenAI-style request to your ElevenLabs function
+        result = generate_speech(
+            model=request.model,
+            voice=request.voice,
+            input_text=request.input
+        )
+        
+        if isinstance(result, list):
+            # If result is a list, it means there was an error
+            raise HTTPException(status_code=result[0], detail=result[1])
+        
+        # If successful, return the audio content
+        return Response(content=result, media_type="audio/mpeg")
+    
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+@app.get("/")
+async def root():
+    return {"message": "Welcome to the Text-to-Speech API"}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=7860)
+
+    # print("Sample URL: http://localhost:7860/v1/audio/speech?model=eleven_multilingual_v2&input=Hello+world&voice=XB0fDUnXU5powFXDhCwa")
+
+