Create tts_app.py

tts_app.py

@@ -0,0 +1,30 @@
+import gradio as gr
+import edge_tts
+import asyncio
+import tempfile
+
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None
+    voice_short_name = voice.split(" - ")[0]
+    communicate = edge_tts.Communicate(text, voice_short_name, rate=f"{rate:+d}%", pitch=f"{pitch:+d}Hz")
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp:
+        await communicate.save(tmp.name)
+        return tmp.name
+
+async def build_ui():
+    voices = await edge_tts.list_voices()
+    voice_map = {f"{v['ShortName']} - {v['Locale']}": v['ShortName'] for v in voices}
+    with gr.Blocks() as demo:
+        gr.Markdown("# 🗣️ Text to Speech")
+        text_in = gr.Textbox(label="Text", lines=4)
+        voice = gr.Dropdown(choices=list(voice_map.keys()), label="Voice")
+        rate = gr.Slider(-50, 50, 0, step=1, label="Rate (%)")
+        pitch = gr.Slider(-20, 20, 0, step=1, label="Pitch (Hz)")
+        out = gr.Audio(label="Generated Speech", type="filepath")
+        btn = gr.Button("Generate")
+        btn.click(lambda t, v, r, p: asyncio.run(text_to_speech(t, v, r, p)),
+                  inputs=[text_in, voice, rate, pitch], outputs=out)
+    return demo
+
+demo = asyncio.run(build_ui())