Add audio, scripts, and captcha generation tools

Added new media files (video, audio, subtitles), two scripts for audio combination and captcha audio generation, and updated main.py and server.py for voice and speed settings. Script files were revised for clarity and additional instructions, supporting new workflow for proctor scheduling system documentation and audio generation.
2025-11-21 10:09:24 -05:00
parent 6137591566
commit 9a5e776dab
11 changed files with 1089 additions and 24 deletions
--- a/main.py
+++ b/main.py
@@ -501,7 +501,7 @@ content = ' '.join(content.splitlines())
 # Option 1: Let the model handle its own splitting by not providing a split pattern:
 generator = pipeline(
    content, voice='af_heart',  # Change voice if desired
-    speed=0.85
+    speed=0.8
 )

 # Option 2: Alternatively, use a regex that splits on sentence boundaries (uncomment to use):