Update app.py

app.py

@@ -1,36 +1,39 @@
-import gradio as gr
+import os
 import numpy as np
+import torch
+import scipy
+import gradio as gr
+
 from bark import generate_audio, preload_models
 from bark.generation import SAMPLE_RATE
 
-# Load models (this takes ~1 min on first load)
+# Preload bark models
 preload_models()
 
-# Function for generating voice
-def bark_tts(text, voice):
-    audio_array = generate_audio(text, history_prompt=voice)
-    return SAMPLE_RATE, audio_array
+def bark_tts(text, speaker="v2/en_speaker_6"):
+    try:
+        audio_array = generate_audio(text, history_prompt=speaker)
+        return SAMPLE_RATE, audio_array
+    except Exception as e:
+        return f"Error: {str(e)}", None
 
-# Gradio Interface
-interface = gr.Interface(
+voices = [
+    "v2/en_speaker_0",
+    "v2/en_speaker_1",
+    "v2/en_speaker_6",
+    "v2/en_speaker_9",
+]
+
+gr.Interface(
     fn=bark_tts,
     inputs=[
-        gr.Textbox(lines=3, label="Enter Text"),
-        gr.Dropdown(
-            choices=[
-                "v2/en_speaker_1",
-                "v2/en_speaker_3",
-                "v2/en_speaker_6",
-                "v2/en_speaker_8",
-                "v2/en_speaker_9"
-            ],
-            value="v2/en_speaker_1",
-            label="Choose Voice"
-        )
+        gr.Textbox(label="Enter Text"),
+        gr.Dropdown(choices=voices, label="Select Voice", value="v2/en_speaker_6")
     ],
-    outputs=gr.Audio(label="Generated Voice", type="numpy"),
-    title="🎙️ Bark AI VoiceBot",
-    description="Convert text to realistic AI voice using Bark TTS"
-)
-
-interface.launch()
+    outputs=[
+        gr.Audio(label="Generated Voice")
+    ],
+    title="Text-to-Speech using Bark",
+    description="Type a sentence and choose a voice to generate TTS.",
+    live=False
+).launch()