Create app.py

app.py

@@ -0,0 +1,53 @@
+import gradio as gr
+import requests
+import os
+
+# Define the API URLs for both languages
+# We use Meta's MMS models which are excellent for both
+MODELS = {
+    "English": "https://api-inference.huggingface.co/models/facebook/mms-tts-eng",
+    "Yoruba": "https://api-inference.huggingface.co/models/facebook/mms-tts-yor"
+}
+
+# Get token from environment variables
+hf_token = os.getenv("HF_TOKEN")
+headers = {"Authorization": f"Bearer {hf_token}"}
+
+def text_to_speech(text, language):
+    # Select the correct URL based on user choice
+    api_url = MODELS[language]
+    
+    # Send request to Hugging Face
+    try:
+        response = requests.post(api_url, headers=headers, json={"inputs": text})
+        response.raise_for_status() # Check for errors
+    except Exception as e:
+        return None, f"Error: {str(e)}"
+
+    # Save audio to file
+    output_file = "output.wav"
+    with open(output_file, "wb") as f:
+        f.write(response.content)
+    
+    return output_file, None
+
+# Create the Interface
+with gr.Blocks() as demo:
+    gr.Markdown("# 🇳🇬 English & Yoruba Text-to-Speech")
+    
+    with gr.Row():
+        # Input Text
+        txt_input = gr.Textbox(label="Enter Text", placeholder="Type something here...")
+        # Language Dropdown
+        lang_dropdown = gr.Dropdown(choices=["English", "Yoruba"], value="English", label="Select Language")
+    
+    # Run Button
+    btn = gr.Button("Generate Audio")
+    
+    # Output Audio
+    audio_out = gr.Audio(label="Output Audio")
+    
+    # Connect the button to the function
+    btn.click(fn=text_to_speech, inputs=[txt_input, lang_dropdown], outputs=[audio_out])
+
+demo.launch()