Add application file

.gitignore

@@ -0,0 +1,3 @@
+.venv
+.gradio
+flagged

app.py

@@ -0,0 +1,90 @@
+import gradio as gr
+import edge_tts
+import asyncio
+import tempfile
+import os
+
+
+async def get_voices():
+    voices = await edge_tts.list_voices()
+    return {
+        f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v["ShortName"]
+        for v in voices
+    }
+
+
+async def text_to_speech(text, voice, rate, pitch):
+    if not text.strip():
+        return None, "Please enter text to convert."
+    if not voice:
+        return None, "Please select a voice."
+
+    voice_short_name = voice.split(" - ")[0]
+    rate_str = f"{rate:+d}%"
+    pitch_str = f"{pitch:+d}Hz"
+    communicate = edge_tts.Communicate(
+        text, voice_short_name, rate=rate_str, pitch=pitch_str
+    )
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".mp3") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return tmp_path, None
+
+
+async def tts_interface(text, voice, rate, pitch):
+    audio, warning = await text_to_speech(text, voice, rate, pitch)
+    if warning:
+        return audio, gr.Warning(warning)
+    return audio, None
+
+
+async def create_demo():
+    voices = await get_voices()
+
+    description = """
+    Convert text to speech using Microsoft Edge TTS. Adjust speech rate and pitch: 0 is default, positive values increase, negative values decrease.
+    
+    **Note:** Edge TTS is a cloud-based service and requires an active internet connection."""
+
+    demo = gr.Interface(
+        fn=tts_interface,
+        inputs=[
+            gr.Textbox(label="Input Text", lines=5, value="Hello, how are you doing!"),
+            gr.Dropdown(
+                choices=[""] + list(voices.keys()),
+                label="Select Voice",
+                value=list(voices.keys())[0] if voices else "",
+            ),
+            gr.Slider(
+                minimum=-50,
+                maximum=50,
+                value=0,
+                label="Speech Rate Adjustment (%)",
+                step=1,
+            ),
+            gr.Slider(
+                minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1
+            ),
+        ],
+        outputs=[
+            gr.Audio(label="Generated Audio", type="filepath"),
+            gr.Markdown(label="Warning", visible=False),
+        ],
+        title="Edge TTS Text-to-Speech",
+        description=description,
+        article="Experience the power of Edge TTS for text-to-speech conversion, and explore our advanced Text-to-Video Converter for even more creative possibilities!",
+        analytics_enabled=False,
+        flagging_mode="manual",  
+        api_name="predict",
+    )
+    return demo
+
+
+async def main():
+    demo = await create_demo()
+    demo.queue(default_concurrency_limit=50)
+    demo.launch(show_api=True, show_error=True)
+
+
+if __name__ == "__main__":
+    asyncio.run(main())

requirements.txt

@@ -0,0 +1,3 @@
+edge_tts==6.1.12
+gradio==5.24.0
+pydub==0.25.1