thinksound
a unified Any2Audio generation framework guided by Chain-of-Thought (CoT) reasoning
Installation
In a virtualenv (see these instructions if you need to create one):
pip3 install thinksound
Dependencies
- descript-audio-codec
- laion-clap
- wandb
- opencv-python
- v-diffusion-pytorch
- pedalboard
- sentencepiece
- importlib-resources
- lightning
- ema-pytorch
- local-attention
- alias-free-torch
- gradio
- encodec
- torch
- vector-quantize-pytorch
- safetensors
- torchmetrics
- tqdm
- huggingface-hub
- pandas
- pywavelets
- open-clip-torch
- einops
- prefigure
- x-transformers
- k-diffusion
- auraloss
- aeiou
- torchaudio
- transformers
- pytorch-lightning
- s3fs
- einops-exts
- omegaconf
- webdataset
Releases
| Version | Released | Bullseye Python 3.9 |
Bookworm Python 3.11 |
Trixie Python 3.13 |
Files |
|---|---|---|---|---|---|
| 0.0.19 | 2025-07-17 | ||||
|
|||||
| 0.0.18 | 2025-07-17 | ||||
|
|||||
| 0.0.17 | 2025-07-16 | ||||
|
|||||
| 0.0.16 | 2025-07-15 | ||||
|
|||||
Issues with this package?
- Search issues for this package
- Package or version missing? Open a new issue
- Something else? Open a new issue