Create app.py

app.py

@@ -0,0 +1,46 @@
+import gradio as gr
+import requests
+import uuid  # For generating unique temporary file names
+
+# Define available speakers (update with real speaker options from the Kokoro-TTS model)
+AVAILABLE_SPEAKERS = ["Speaker 1", "Speaker 2", "Speaker 3"]
+
+# Function to interact with Kokoro-TTS API and generate speech
+def generate_tts(text, speaker):
+    # Kokoro-TTS Space endpoint
+    url = "https://hexgrad-kokoro-tts.hf.space/api/predict"
+    payload = {
+        "data": [text, speaker]  # Send text and speaker selection to API
+    }
+    response = requests.post(url, json=payload)
+    
+    if response.status_code == 200:
+        output = response.json()
+        audio_data = output["data"][0]  # Get the generated audio binary
+        temp_filename = f"output_{uuid.uuid4().hex}.wav"  # Generate a unique temporary name
+        with open(temp_filename, "wb") as f:
+            f.write(audio_data.encode('latin1'))  # Decode and save the binary data as a WAV file
+        return temp_filename, temp_filename
+    else:
+        return None, "Error: Unable to generate TTS"
+
+# Gradio Interface
+with gr.Blocks() as app:
+    gr.Markdown("## Long Text-to-Speech Generator with Kokoro-TTS")
+    
+    with gr.Row():
+        input_text = gr.Textbox(label="Enter your text", placeholder="Type or paste your text here...", lines=10)
+        speaker_dropdown = gr.Dropdown(choices=AVAILABLE_SPEAKERS, label="Select Speaker")
+    
+    with gr.Row():
+        generate_button = gr.Button("Generate Speech")
+    
+    with gr.Row():
+        audio_output = gr.Audio(label="Generated Speech", type="file", interactive=False)
+        download_button = gr.File(label="Download Audio", file_types=[".wav", ".mp3"])
+    
+    # Link the generate button to the TTS generation function
+    generate_button.click(fn=generate_tts, inputs=[input_text, speaker_dropdown], outputs=[audio_output, download_button])
+
+# Launch the app
+app.launch()