Update app.py

app.py

@@ -5,57 +5,31 @@ import time
 import subprocess
 import gradio as gr
 import uuid
+import edge_tts
 from dotenv import load_dotenv
 
 # Load environment variables
 load_dotenv()
 
 # API Keys
-A_KEY = os.getenv("A_KEY")
 B_KEY = os.getenv("B_KEY")
 
 # URLs
 API_URL = os.getenv("API_URL")
 UPLOAD_URL = os.getenv("UPLOAD_URL")
 
-def get_voices():
-    url = "https://api.elevenlabs.io/v1/voices"
-    headers = {
-        "Accept": "application/json",
-        "xi-api-key": A_KEY
-    }
-    
-    response = requests.get(url, headers=headers)
-    if response.status_code != 200:
-        return []
-    return [(voice['name'], voice['voice_id']) for voice in response.json().get('voices', [])]
+# Fetch voices from edge_tts
+async def get_edge_tts_voices():
+    voices = await edge_tts.list_voices()
+    return [(voice['Name'], voice['ShortName']) for voice in voices]
 
-def text_to_speech(voice_id, text, session_id):
-    url = f"https://api.elevenlabs.io/v1/text-to-speech/{voice_id}"
-    
-    headers = {
-        "Accept": "audio/mpeg",
-        "Content-Type": "application/json",
-        "xi-api-key": A_KEY
-    }
-    
-    data = {
-        "text": text,
-        "model_id": "eleven_turbo_v2_5",
-        "voice_settings": {
-            "stability": 0.5,
-            "similarity_boost": 0.5
-        }
-    }
+# Text-to-speech using edge_tts
+async def text_to_speech(voice_id, text, session_id):
+    audio_file_path = f'temp_voice_{session_id}.mp3'
     
-    response = requests.post(url, json=data, headers=headers)
-    if response.status_code != 200:
-        return None
+    communicate = edge_tts.Communicate(text, voice_id)
+    await communicate.save(audio_file_path)
     
-    # Save temporary audio file with session ID
-    audio_file_path = f'temp_voice_{session_id}.mp3'
-    with open(audio_file_path, 'wb') as audio_file:
-        audio_file.write(response.content)
     return audio_file_path
 
 def upload_file(file_path):
@@ -136,10 +110,10 @@ def combine_audio_video(video_path, audio_path, output_path):
 
     subprocess.run(cmd, check=True)
 
-def process_video(voice, video_url, text, progress=gr.Progress()):
+async def process_video(voice, video_url, text, progress=gr.Progress()):
     session_id = str(uuid.uuid4())  # Generate a unique session ID
     progress(0, desc="Generating speech...")
-    audio_path = text_to_speech(voice, text, session_id)
+    audio_path = await text_to_speech(voice, text, session_id)
     if not audio_path:
         return None, "Failed to generate speech audio."
     
@@ -197,13 +171,19 @@ def process_video(voice, video_url, text, progress=gr.Progress()):
             os.remove(f"temp_video_{session_id}.mp4")
 
 def create_interface():
-    voices = get_voices()
+    voices = []
+    
+    # Asynchronous Gradio callback for fetching voices
+    async def async_get_voices():
+        nonlocal voices
+        voices = await get_edge_tts_voices()
+        return [v[0] for v in voices]
     
     with gr.Blocks() as app:
         gr.Markdown("# JSON Train")
         with gr.Row():
             with gr.Column():
-                voice_dropdown = gr.Dropdown(choices=[v[0] for v in voices], label="Select Voice", value=voices[0][0] if voices else None)
+                voice_dropdown = gr.Dropdown(choices=await async_get_voices(), label="Select Voice")
                 video_url_input = gr.Textbox(label="Enter Video URL")
                 text_input = gr.Textbox(label="Enter text", lines=3)
                 generate_btn = gr.Button("Generate Video")
@@ -227,4 +207,4 @@ def create_interface():
 
 if __name__ == "__main__":
     app = create_interface()
-    app.launch()
+    app.launch()