Create app.py

app.py

@@ -0,0 +1,34 @@
+import gradio as gr
+from TTS.api import TTS
+import tempfile
+import os
+
+tts = TTS("tts_models/multilingual/multi-dataset/xtts_v2", gpu=True)
+
+def clone(text, speaker_wav):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as f:
+        f.write(speaker_wav)
+        ref = f.name
+
+    out = ref.replace(".wav", "_out.wav")
+
+    tts.tts_to_file(
+        text=text,
+        speaker_wav=ref,
+        language="en",
+        file_path=out
+    )
+
+    return out
+
+ui = gr.Interface(
+    fn=clone,
+    inputs=[
+        gr.Textbox(label="Text"),
+        gr.Audio(type="numpy", label="Reference Voice")
+    ],
+    outputs=gr.Audio(label="Cloned Voice"),
+    title="XTTS Voice Clone"
+)
+
+ui.launch()