Update app.py

app.py

@@ -15,10 +15,10 @@ def generate_speech(reference_audio_path, text):
     text: the string to synthesize
     returns: path to a 24 kHz WAV file with your cloned voice
     """
-    # Load the reference clip (Tortoise auto-resamples to 22 050 Hz)
-    ref_waveform = load_audio(reference_audio_path)
+    # ✅ FIXED: Provide sampling_rate as a required positional argument
+    ref_waveform = load_audio(reference_audio_path, 22050)
 
-    # Generate speech using 'fast' preset
+    # Generate speech using 'fast' preset (alternatives: ultra_fast, standard, high_quality)
     output_tensor = tts.tts_with_preset(
         text,
         voice_samples=[ref_waveform],
@@ -33,18 +33,18 @@ def generate_speech(reference_audio_path, text):
 
 # 3) Build the Gradio interface
 with gr.Blocks(title="Tortoise Voice Cloning TTS") as app:
-    gr.Markdown("## Voice Cloning with Tortoise TTS")
+    gr.Markdown("## 🗣️ Voice Cloning with Tortoise TTS")
     gr.Markdown(
         "Upload a ~10 sec WAV clip (22 050 Hz), enter English text, "
         "and hear it spoken back in **your** voice!"
     )
 
     with gr.Row():
-        voice_sample = gr.Audio(type="filepath", label="Upload Reference Voice (22 050 Hz WAV)")
-        text_input   = gr.Textbox(label="Text to Synthesize", placeholder="e.g., Hello, world!")
+        voice_sample = gr.Audio(type="filepath", label="🎙️ Upload Reference Voice (22 050 Hz WAV)")
+        text_input   = gr.Textbox(label="💬 Text to Synthesize", placeholder="e.g., Hello, world!")
 
-    generate_btn = gr.Button("Generate Speech")
-    output_audio = gr.Audio(label="Cloned Speech Output (24 kHz)", interactive=False)
+    generate_btn = gr.Button("🔊 Generate Speech")
+    output_audio = gr.Audio(label="📢 Cloned Speech Output (24 kHz)", interactive=False)
 
     generate_btn.click(
         fn=generate_speech,
@@ -53,4 +53,4 @@ with gr.Blocks(title="Tortoise Voice Cloning TTS") as app:
     )
 
 if __name__ == "__main__":
-    app.launch()
+    app.launch()