We are excited to introduce a fine-tuned version of seed-vc along with the 11labs-train dataset. This model was trained on a curated subset of 5,000 audio files, each ranging from 0 to 20 seconds, from our extensive 175-hour 11labs dataset.
Our goal with this model is to provide the community with a high-quality voice conversation tool, contributing to the broader audio model ecosystem.
For inference: https://github.com/Plachtaa/seed-vc
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no library tag.
Model tree for sleeping-ai/11labs-seed
Base model
Plachta/Seed-VC