Update app.py

app.py

@@ -154,63 +154,50 @@ def use_gtts_for_text(text):
 # Enhanced WebRTC configuration with more STUN/TURN servers
 rtc_configuration = {
     "iceServers": [
-        # Google's public STUN servers
-        {"urls": ["stun:stun.l.google.com:19302", "stun:stun1.l.google.com:19302", "stun:stun2.l.google.com:19302", "stun:stun3.l.google.com:19302", "stun:stun4.l.google.com:19302"]},
-        
-        # OpenRelay TURN servers (HTTP)
+        {"urls": ["stun:stun.l.google.com:19302", "stun:stun1.l.google.com:19302"]},
         {
             "urls": ["turn:openrelay.metered.ca:80"],
             "username": "openrelayproject",
             "credential": "openrelayproject"
         },
-        
-        # OpenRelay TURN servers (HTTPS)
-        {
-            "urls": ["turn:openrelay.metered.ca:443"],
-            "username": "openrelayproject", 
-            "credential": "openrelayproject"
-        },
-        
-        # OpenRelay TURN servers (TCP)
         {
             "urls": ["turn:openrelay.metered.ca:443?transport=tcp"],
             "username": "openrelayproject",
             "credential": "openrelayproject"
-        },
-        
-        # Additional public STUN servers
-        {"urls": ["stun:stun.stunprotocol.org:3478"]}
+        }
     ],
-    "iceCandidatePoolSize": 10  # Increase the pool size
+    "iceCandidatePoolSize": 10
 }
 
-# Set WebRTC logging level to "debug" for more information
-os.environ["WEBRTC_TRACE"] = "WEBRTC_TRACE_ALL"
+# Create Gradio chatbot and stream - following the exact cookbook pattern
+chatbot = gr.Chatbot(type="messages")
+stream = Stream(
+    modality="audio",
+    mode="send-receive",
+    handler=ReplyOnPause(response, input_sample_rate=16000),
+    additional_outputs_handler=lambda a, b: b,
+    additional_inputs=[chatbot],
+    additional_outputs=[chatbot],
+    rtc_configuration=rtc_configuration,
+    concurrency_limit=5 if get_space() else None,
+    time_limit=90 if get_space() else None,
+    ui_args={"title": "LLM Voice Chat (Powered by DeepSeek & ElevenLabs)"}
+)
+
+# Mount the Stream UI to FastAPI
+app = FastAPI()
+app = gr.mount_gradio_app(app, stream.ui, path="/")
 
-# Create Gradio interface with simple structure
-with gr.Blocks(title="LLM Voice Chat") as demo:
-    gr.Markdown("# LLM Voice Chat (Powered by DeepSeek & ElevenLabs)")
+# Only for local development
+if __name__ == "__main__":
+    import uvicorn
     
-    with gr.Row():
-        chatbot = gr.Chatbot(type="messages", label="Chat History")
+    os.environ["GRADIO_SSR_MODE"] = "false"
     
-    with gr.Row():
-        # Create the Stream component for handling audio
-        stream_comp = Stream(
-            modality="audio",
-            mode="send-receive",
-            handler=ReplyOnPause(response, input_sample_rate=16000),
-            additional_outputs_handler=lambda a, b: b,
-            additional_inputs=[chatbot],
-            additional_outputs=[chatbot],
-            rtc_configuration=rtc_configuration,
-            concurrency_limit=5 if get_space() else None,
-            time_limit=90 if get_space() else None,
-        )
-        
-        # Make sure to render the Stream component
-        stream_comp.render()
-
-# For local development only
-if __name__ == "__main__" and not get_space():
-    demo.launch(share=True)
+    if get_space():
+        # When running in HF Spaces, use their port and host
+        port = int(os.environ.get("PORT", 7860))
+        uvicorn.run(app, host="0.0.0.0", port=port)
+    else:
+        # For local development
+        stream.ui.launch(server_port=7860)