Update app.py

app.py

@@ -8,49 +8,49 @@ import srt
 from pydub import AudioSegment, silence
 import datetime
 
-# 📦 Safe punkt download (for Hugging Face Spaces)
+# 📦 Safe punkt download
 nltk_data_path = os.path.join(os.path.expanduser("~"), "nltk_data")
 nltk.download("punkt", download_dir=nltk_data_path)
 nltk.data.path.append(nltk_data_path)
 
-# 🔊 Generate TTS audio
+# 🔊 Generate audio
 async def text_to_speech(text, voice, rate, pitch):
     if not text.strip():
-        return None, None, "Please enter text to convert."
+        return None, None, "Please enter some text."
     if not voice:
         return None, None, "Please select a voice."
 
-    voice_short_name = voice.split(" - ")[0]
+    voice_short = 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)
+    communicate = edge_tts.Communicate(text, voice_short, 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)
 
-    # Generate SRT
+    # SRT generation
     srt_path = generate_srt(tmp_path, text)
+    return tmp_path, srt_path, ""
 
-    return tmp_path, srt_path, None
-
-# 🧠 Generate SRT from audio + text
+# 🧠 Generate subtitles
 def generate_srt(audio_path, text):
     audio = AudioSegment.from_file(audio_path)
-    silence_ranges = silence.detect_silence(audio, min_silence_len=400, silence_thresh=audio.dBFS - 16)
-    silence_ranges = [(start / 1000.0, end / 1000.0) for start, end in silence_ranges]
-    sentences = nltk.tokenize.sent_tokenize(text)
+    silences = silence.detect_silence(audio, min_silence_len=400, silence_thresh=audio.dBFS - 16)
+    silences = [(start / 1000.0, end / 1000.0) for start, end in silences]
 
+    sentences = nltk.tokenize.sent_tokenize(text)
     subtitles = []
     last_time = 0.0
+
     for i, sentence in enumerate(sentences):
-        if i < len(silence_ranges):
+        if i < len(silences):
             start = last_time
-            end = silence_ranges[i][0]
-            last_time = silence_ranges[i][1]
+            end = silences[i][0]
+            last_time = silences[i][1]
         else:
             start = last_time
-            end = start + 2.5  # fallback timing
+            end = start + 2.5
         subtitles.append(srt.Subtitle(
             index=i + 1,
             start=datetime.timedelta(seconds=start),
@@ -59,50 +59,49 @@ def generate_srt(audio_path, text):
         ))
 
     srt_data = srt.compose(subtitles)
-    with tempfile.NamedTemporaryFile(delete=False, suffix=".srt", mode='w') as srt_file:
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".srt", mode="w") as srt_file:
         srt_file.write(srt_data)
         return srt_file.name
 
-# 🎛️ Interface wrapper
+# Interface wrapper
 async def tts_interface(text, voice, rate, pitch):
-    audio, srt_file, warning = await text_to_speech(text, voice, rate, pitch)
-    if warning:
-        return None, None, gr.Warning(warning)
-    return audio, srt_file, None
+    audio_path, srt_path, message = await text_to_speech(text, voice, rate, pitch)
+    return audio_path, srt_path, message
 
-# 📋 Setup Gradio UI
+# UI setup
 async def create_demo():
     voices = await edge_tts.list_voices()
     voice_dict = {f"{v['ShortName']} - {v['Locale']} ({v['Gender']})": v['ShortName'] for v in voices}
 
     with gr.Blocks() as demo:
-        gr.Markdown("# 🎙️ Edge TTS + Subtitle Generator (.srt)")
+        gr.Markdown("# 🎙️ Text-to-Speech + Subtitle Generator")
 
         with gr.Row():
             with gr.Column():
-                text_input = gr.Textbox(label="Input Text", lines=5, placeholder="Enter your script here...")
-                voice_dropdown = gr.Dropdown(choices=[""] + list(voice_dict.keys()), label="Select Voice", value="")
+                text_input = gr.Textbox(label="Input Text", lines=5)
+                voice_dropdown = gr.Dropdown(choices=[""] + list(voice_dict.keys()), label="Select Voice")
                 rate_slider = gr.Slider(minimum=-50, maximum=50, value=0, label="Speech Rate (%)")
                 pitch_slider = gr.Slider(minimum=-20, maximum=20, value=0, label="Pitch (Hz)")
                 generate_btn = gr.Button("🎧 Generate Audio + SRT")
 
             with gr.Column():
                 audio_output = gr.Audio(label="Generated Audio", type="filepath")
-                srt_output = gr.File(label="Download .srt Subtitle")
-                warning_output = gr.Markdown(visible=False)
+                srt_output = gr.File(label="Download Subtitle (.srt)")
+                message_output = gr.Textbox(label="Status", interactive=False)
 
         generate_btn.click(
             fn=tts_interface,
             inputs=[text_input, voice_dropdown, rate_slider, pitch_slider],
-            outputs=[audio_output, srt_output, warning_output]
+            outputs=[audio_output, srt_output, message_output]
         )
 
     return demo
 
+# Entry point
 async def main():
     demo = await create_demo()
     demo.queue()
-    await demo.launch()  # ✅ note: `await` is needed here
+    await demo.launch()
 
 if __name__ == "__main__":
     asyncio.run(main())