yt-dlp>=2024.0
openai>=1.0
json-repair>=0.28
Pillow>=10.0
soundfile>=0.12
numpy>=1.24
tqdm>=4.60
python-slugify>=8.0

[all-chatterbox]
mazinger[audio-enhance,transcribe-faster,tts-chatterbox]

[all-mlx]
mazinger[transcribe-faster,transcribe-mlx,tts-mlx]

[all-qwen]
mazinger[audio-enhance,transcribe-faster,tts]

[audio-enhance]
demucs>=4.0.1

[flash-attn]
flash-attn>=2.0

[transcribe]
mazinger[transcribe-faster]

[transcribe-faster]
faster-whisper>=1.0

[transcribe-mlx]
mlx-whisper>=0.4

[transcribe-whisperx]
whisperx>=3.8.4
pyannote.audio>=4.0
torch>=2.0
scipy>=1.14
scikit-learn>=1.5

[tts]
qwen-tts
torch>=2.0
soundfile>=0.12

[tts-chatterbox]
chatterbox-tts
resemble-perth>=1.0.1
torch>=2.0
torchaudio>=2.0
soundfile>=0.12
numpy>=1.26
pandas>=2.2

[tts-mlx]
mlx-audio>=0.4.2
mlx>=0.20
soundfile>=0.12
