Files
voicebox/backend/requirements.txt
James Pine fc5ed1ff40 upgrade CUDA backend from cu126 to cu128 and fix GPU settings UI
Upgrade CUDA toolkit from 12.6 (cu126) to 12.8 (cu128) for proper
RTX 50-series (Blackwell) GPU support. Users with RTX 5070/5080/5090
were reporting CUDA detection failures with cu126.

Also fix the GPU Acceleration settings panel where the 'Switch to CPU
Backend' button was unreachable — it was inside a conditional block
that required !isCurrentlyCuda, making it impossible to switch back
to CPU once running on CUDA.

Closes #315
2026-03-18 07:47:39 -07:00

56 lines
1.4 KiB
Plaintext

# FastAPI and server
fastapi>=0.109.0
uvicorn[standard]>=0.27.0
pydantic>=2.5.0
# Database
sqlalchemy>=2.0.0
alembic>=1.13.0
# ML models
torch>=2.7.0
transformers>=4.36.0,<=4.57.6
accelerate>=0.26.0
huggingface_hub>=0.20.0
qwen-tts>=0.0.5
# LuxTTS (voice cloning engine)
# piper-phonemize needs custom index (no PyPI wheels)
--find-links https://k2-fsa.github.io/icefall/piper_phonemize.html
# linacodec is a git-only dep of Zipvoice (uv-only source, pip can't resolve it)
linacodec @ git+https://github.com/ysharma3501/LinaCodec.git
Zipvoice @ git+https://github.com/ysharma3501/LuxTTS.git
# Chatterbox TTS sub-dependencies (chatterbox-tts itself is installed
# --no-deps in the setup script because it pins numpy<1.26 / torch==2.6
# which are incompatible with Python 3.12+)
conformer>=0.3.2
diffusers>=0.29.0
omegaconf
pykakasi
resemble-perth>=1.0.1
s3tokenizer
spacy-pkuseg
pyloudnorm
# HumeAI TADA sub-dependencies (hume-tada itself is installed
# --no-deps in the setup script because it pins torch>=2.7,<2.8.
# descript-audio-codec is NOT installed — it pulls onnx/tensorboard
# via descript-audiotools. A lightweight shim in utils/dac_shim.py
# provides the only class TADA uses: Snake1d.)
torchaudio
# Audio processing
librosa>=0.10.0
soundfile>=0.12.0
numpy>=1.24.0
numba>=0.60.0,<0.61.0
pedalboard>=0.9.0
# HTTP client (for CUDA backend download)
httpx>=0.27.0
# Utilities
python-multipart>=0.0.6
Pillow>=10.0.0