YigitSekerci commited on
Commit
9afb0c3
Β·
1 Parent(s): 5720b20

add guidelines

Browse files
Files changed (1) hide show
  1. src/ui.py +37 -3
src/ui.py CHANGED
@@ -129,8 +129,8 @@ def create_interface():
129
  theme=gr.themes.Default(),
130
  ) as interface:
131
  gr.Markdown("""
132
- # 🎡 Audio Agent - Professional Audio Processing
133
- **Supported formats**: MP3, WAV, M4A, FLAC, AAC, OGG
134
  """)
135
 
136
  # Hidden state to store audio file URLs and custom history
@@ -227,7 +227,41 @@ def create_interface():
227
  [chatbot, audio_urls_state, custom_history_state],
228
  [chatbot, output_audio_files, custom_history_state]
229
  )
230
-
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
231
  return interface
232
 
233
  if __name__ == "__main__":
 
129
  theme=gr.themes.Default(),
130
  ) as interface:
131
  gr.Markdown("""
132
+ # Audio Agent - Your AI Audio Assistant
133
+ Upload your audio files and tell me what you need. I'll handle the rest!
134
  """)
135
 
136
  # Hidden state to store audio file URLs and custom history
 
227
  [chatbot, audio_urls_state, custom_history_state],
228
  [chatbot, output_audio_files, custom_history_state]
229
  )
230
+
231
+ gr.Markdown("""
232
+ ---
233
+ """)
234
+
235
+ with gr.Row():
236
+ gr.Markdown("""
237
+
238
+ ## 🎚️ What I Can Do For You
239
+
240
+ **Audio Manipulation:**
241
+ - Merge multiple audio files into one continuous track
242
+ - Cut or trim specific sections from any file
243
+ - Adjust volume levels (increase or decrease)
244
+ - Normalize audio levels for consistency
245
+ - Apply fade-in or fade-out effects for smooth transitions (Mono channel only)
246
+ - Change playback speed (faster or slower, with pitch change)
247
+ - Reverse audio for creative effects
248
+ - Remove silence from beginning or end of files
249
+
250
+ **Analysis & Transcription:** (English only)
251
+ - Transcribe speech in audio to text
252
+ - Analyze audio properties (duration, sample rate, etc.)
253
+ """)
254
+ gr.Markdown("""
255
+ ## πŸ’‘ Example Requests
256
+
257
+ - *"Merge these two audio files and add a fade-in effect"*
258
+ - *"Remove the silence at the beginning of this recording"*
259
+ - *"Transcribe the speech in this audio file"*
260
+ - *"Increase the volume of the first track and normalize both files"*
261
+ - *"Cut out the middle section from 1:30 to 2:45"*
262
+ - *"Make this audio play 1.5x faster"*
263
+ - *"Apply a fade-out effect to the end of this track"*
264
+ """)
265
  return interface
266
 
267
  if __name__ == "__main__":