Update app.py

app.py

@@ -8,7 +8,7 @@ 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):
+async def text_to_speech(text, voice, rate, volume, pitch):
     if not text.strip():
         return None, "Please enter text to convert."
     if not voice:
@@ -16,15 +16,16 @@ async def text_to_speech(text, voice, rate, pitch):
     
     voice_short_name = voice.split(" - ")[0]
     rate_str = f"{rate:+d}%"
+    volume_str = f"{volume:+d}%"
     pitch_str = f"{pitch:+d}Hz"
-    communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, pitch=pitch_str)
+    communicate = edge_tts.Communicate(text, voice_short_name, rate=rate_str, volume=volume_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)
+async def tts_interface(text, voice, rate, volume, pitch):
+    audio, warning = await text_to_speech(text, voice, rate, volume, pitch)
     if warning:
         return audio, gr.Warning(warning)
     return audio, None
@@ -53,6 +54,7 @@ async def create_demo():
             gr.Textbox(label="Input Text", lines=5),
             gr.Dropdown(choices=[""] + list(voices.keys()), label="Select Voice", value=""),
             gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate Adjustment (%)", step=1),
+            gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Volume Adjustment (%)", step=1),
             gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch Adjustment (Hz)", step=1)
         ],
         outputs=[