Update app.py

app.py

@@ -7,10 +7,10 @@
 import os
 import gradio as gr
 import openai
-from elevenlabs import generate, set_api_key
 import tempfile
 import logging
 from dotenv import load_dotenv
+import requests
 
 # Load environment variables from .env file
 load_dotenv()
@@ -33,9 +33,36 @@ if not eleven_labs_api_key:
 else:
     logger.info("Eleven Labs API key is set.")
 
-# Set the API keys
+# Set the API key for OpenAI
 openai.api_key = openai_api_key
-set_api_key(eleven_labs_api_key)
+
+def text_to_speech_elevenlabs(text, voice="Rachel"):
+    url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice}"
+
+    headers = {
+        "Accept": "audio/mpeg",
+        "Content-Type": "application/json",
+        "xi-api-key": eleven_labs_api_key
+    }
+
+    data = {
+        "text": text,
+        "model_id": "eleven_multilingual_v1",
+        "voice_settings": {
+            "stability": 0.5,
+            "similarity_boost": 0.75
+        }
+    }
+
+    response = requests.post(url, json=data, headers=headers)
+    response.raise_for_status()
+
+    # Save the audio content
+    temp_audio_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp3')
+    with open(temp_audio_file.name, 'wb') as f:
+        f.write(response.content)
+
+    return temp_audio_file.name
 
 def process_audio(audio_file, target_language):
     try:
@@ -51,8 +78,14 @@ def process_audio(audio_file, target_language):
     try:
         # Translate text using OpenAI's ChatGPT API
         messages = [
-            {"role": "system", "content": f"You are a helpful assistant that translates English to {target_language}."},
-            {"role": "user", "content": f"Please translate the following text to {target_language}: {user_text}"}
+            {
+                "role": "system",
+                "content": f"You are a helpful assistant that translates English to {target_language}."
+            },
+            {
+                "role": "user",
+                "content": f"Please translate the following text to {target_language}: {user_text}"
+            }
         ]
 
         response = openai.ChatCompletion.create(
@@ -67,24 +100,33 @@ def process_audio(audio_file, target_language):
         return "Error in generating translation.", None
 
     try:
-        # Convert translated text to speech using Eleven Labs
-        audio = generate(
-            text=response_text,
-            voice="Rachel",  # You can choose different voices available in Eleven Labs
-            model='eleven_multilingual_v1'  # Use the multilingual model
-        )
-
-        # Save the audio to a temporary file
-        temp_audio_file = tempfile.NamedTemporaryFile(delete=False, suffix='.mp3')
-        with open(temp_audio_file.name, 'wb') as f:
-            f.write(audio)
-
+        # Convert translated text to speech using Eleven Labs API directly
+        temp_audio_file_name = text_to_speech_elevenlabs(response_text)
         logger.info("Text-to-speech conversion successful.")
     except Exception as e:
         logger.error(f"Error in text-to-speech conversion: {e}")
         return "Error in text-to-speech conversion.", None
 
-    return response_text, temp_audio_file.name
+    return response_text, temp_audio_file_name
+
+# Optional: Function to list available voices
+def list_available_voices():
+    url = "https://api.elevenlabs.io/v1/voices"
+
+    headers = {
+        "Accept": "application/json",
+        "xi-api-key": eleven_labs_api_key
+    }
+
+    response = requests.get(url, headers=headers)
+    response.raise_for_status()
+    voices = response.json()
+    print("Available voices:")
+    for voice in voices['voices']:
+        print(f"Name: {voice['name']}, Voice ID: {voice['voice_id']}")
+
+# Uncomment the following line to list available voices
+# list_available_voices()
 
 # Create Gradio interface
 iface = gr.Interface(
@@ -112,4 +154,3 @@ try:
 except Exception as e:
     logger.error(f"Failed to launch Gradio interface: {e}")
     raise
-