Create app.py

app.py

@@ -0,0 +1,34 @@
+import os
+import gradio as gr
+from TTS.api import TTS
+import torch
+import spaces 
+
+# License accept
+os.environ["COQUI_TOS_AGREED"] = "1"
+
+# Model load (Wait for 2-3 mins first time)
+device = "cuda" if torch.cuda.is_available() else "cpu"
+tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2").to(device)
+
+@spaces.GPU(duration=60) 
+def clone_voice(text, language, speaker_audio):
+    output_path = "output.wav"
+    tts.tts_to_file(
+        text=text,
+        file_path=output_path,
+        speaker_wav=speaker_audio,
+        language=language
+    )
+    return output_path
+
+iface = gr.Interface(
+    fn=clone_voice,
+    inputs=[
+        gr.Textbox(label="Text", value="Namaste, kaise hain aap?"),
+        gr.Dropdown(label="Language", choices=["hi", "en"], value="hi"),
+        gr.Audio(label="Reference Audio", type="filepath")
+    ],
+    outputs=gr.Audio(label="Cloned Voice")
+)
+iface.launch()