Vevo2 / README.md
Vansh Chugh
initial deploy
7afb6d4
|
Raw
History Blame Contribute Delete
684 Bytes
---
title: Vevo2
emoji: 🎤
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.28.0
python_version: '3.11'
app_file: app.py
pinned: false
license: mit
---
# Vevo2
A unified, controllable framework for speech and singing voice generation and conversion. Supports zero-shot voice/singing conversion, text-to-singing, singing editing, singing style conversion, and melody control (hum or play a melody to control a generated vocal).
Paper: [Vevo2: Bridging Controllable Speech and Singing Voice Generation via Unified Prosody Learning](https://arxiv.org/abs/2508.16332)
Source: [open-mmlab/Amphion](https://github.com/open-mmlab/Amphion/blob/main/models/svc/vevo2/README.md)