Document audiocraft incompatibility with Python 3.13

audiocraft (MusicGen) is NOT compatible with Python 3.13 due to:
- audiocraft → spacy → thinc → blis
- blis fails to compile with GCC errors: unrecognized '-mavx512pf' option
- This is a known issue with blis and newer GCC/Python versions

Updated requirements.txt to:
- Remove audiocraft from direct dependencies
- Add note about Python 3.13 incompatibility
- Suggest using Python 3.12 or lower for audiocraft
- Or use a separate Python 3.12 environment for music generation

requirements.txt

@@ -26,7 +26,11 @@ soundfile>=0.12.1
 librosa>=0.10.2
 edge-tts>=6.1.10
 # bark  # Install with: pip install git+https://github.com/suno-ai/bark.git
-# audiocraft  # Install with: pip install audiocraft
+
+# NOTE: audiocraft (MusicGen) is NOT compatible with Python 3.13 due to blis/spacy dependencies
+# For Python 3.12 or lower, you can try:
+# pip install audiocraft
+# For Python 3.13+, use an alternative or wait for audiocraft updates
 
 # Speech-to-Text & Translation (Optional - for dubbing and subtitles)
 openai-whisper>=20231117  # For transcription
@@ -121,10 +125,14 @@ werkzeug>=3.0.1
 #    - pip install dlib
 #    - pip install face-recognition
 #
-# 6. For audiocraft (MusicGen) - requires FFmpeg dev libraries:
-#    - Install system dependencies first (see above)
-#    - pip install av  # May need: pip install av --no-binary av
-#    - pip install audiocraft
+# 6. For audiocraft (MusicGen) - NOT COMPATIBLE WITH PYTHON 3.13:
+#    - audiocraft depends on spacy → thinc → blis
+#    - blis fails to compile on Python 3.13 due to GCC incompatibility
+#    - For Python 3.12 or lower:
+#        pip install av
+#        pip install audiocraft
+#    - For Python 3.13+, use an alternative music generation library or
+#      create a separate Python 3.12 environment for audiocraft
 #
 # 7. For bark (TTS):
 #    pip install git+https://github.com/suno-ai/bark.git