Update readme for more instructions / Update gradio interface for docs

README.md

@@ -83,7 +83,23 @@ Example configuration for a client (like Cline) that supports SSE:
 }
 ```
 
-*Note: If your MCP client does not directly support SSE-based servers (like some versions of Claude Desktop), you may need to use a tool like `mcp-remote` as an intermediary. Refer to your client's documentation for details.*
+*Note: If your MCP client does not directly support SSE-based servers (like Claude Desktop), you may need to use a tool like `mcp-remote` as an intermediary.*
+
+In those cases, you can use a tool such as mcp-remote. First install Node.js. Then, add the following to your own MCP Client config:
+
+```json
+{
+  "mcpServers": {
+    "gradio": {
+      "command": "npx",
+      "args": [
+        "mcp-remote",
+        "http://127.0.0.1:7860/gradio_api/mcp/sse"
+      ]
+    }
+  }
+}
+```
 
 ### Connecting to the Hosted Server on Hugging Face Spaces
 

app.py

@@ -83,13 +83,33 @@ def transcribe_url(url):
 
 
 with gr.Blocks() as app:
-    gr.Markdown("# TranscriptTool: Transcribe Audio/Video")
-    gr.Markdown("TranscriptTool is a smolagent tool used to transcribe audio and video files into text. This tool allows agents to process multimedia inputs efficiently. Can be used within a smolagent via the Hugging Face API.")
+    gr.Markdown("# <center>gradio-transcript-mcp: Transcribe Audio/Video from URL</center>")
+    gr.Markdown(
+        """
+        This application functions as an MCP server that transcribes audio or video from a URL using OpenAI's Whisper model.
+        It downloads the media, converts it to WAV, and performs the transcription.
+
+        ### Connecting to the Hosted Server
+        To connect your MCP client that supports SSE to this hosted server, add a configuration entry similar to this:
+        
+        ```json
+        {
+        "mcpServers": {
+            "gradio-transcript": {
+            "url": "https://bismay-gradio-transcript-mcp.hf.space/gradio_api/mcp/sse"
+            }
+        }
+        }
+        ```
+
+        For more details on setup and MCP usage, see the [README.md](README.md).
+        """
+    )
 
     url_input = gr.Textbox(label="Enter Audio/Video URL", placeholder="e.g., https://www.youtube.com/watch?v=dQw4w9WgXcQ")
     transcribe_button = gr.Button("Transcribe")
 
-    gr.Markdown("Provide a URL to transcribe audio or video.")
+    gr.Markdown("Provide a URL to transcribe audio or YT video.")
 
     transcription_output = gr.Textbox(label="Transcription", lines=10)