Update app.py

app.py

@@ -1,15 +1,34 @@
+import edge_tts
 import gradio as gr
+import tempfile
+import anyio
 
-def text_to_speech(text, voice):
-    import subprocess
-    import audiosegment
+# Define the available languages and their corresponding voices
+language_dict = {
+    "en": "en-US-JennyNeural",
+    "en2": "en-US-GuyNeural",
+    # Add more languages and voices as needed
+}
 
-    command = ['edge-tts', '--voice', voice, '--text', text,
-               '--write-media', 'edge.mp3', '--write-subtitles', 'edge.vtt']
+async def text_to_speech_edge(text, language_code):
+    voice = language_dict.get(language_code, "default_voice")
+    communicate = edge_tts.Communicate(text, voice)
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".wav") as tmp_file:
+        tmp_path = tmp_file.name
+        await communicate.save(tmp_path)
+    return f"Speech synthesis completed for: {text}", tmp_path
 
-    result = subprocess.run(command, stdout=subprocess.PIPE, text=True)
-    print(result.stdout)
+input_text = gr.inputs.Textbox(lines=5, label="Input Text")
+output_text = gr.outputs.Textbox(label="Output Text")
+output_audio = gr.outputs.Audio(type="filepath", label="Exported Audio")
+language = gr.inputs.Dropdown(choices=list(language_dict.keys()), label="Language")
 
-voice = ["en-US-JennyNeural", "en-US-GuyNeural"]
+interface = gr.Interface(
+    fn=text_to_speech_edge,
+    inputs=[input_text, language],
+    outputs=[output_text, output_audio],
+    title="Edge TTS Text-to-Speech"
+)
 
-gr.Interface(fn=text_to_speech, inputs=["text", gr.Dropdown(voice)], outputs="audio").launch()
+if __name__ == "__main__":
+    anyio.run(interface.launch, backend="asyncio")