Promote Sign in Sign up

Multimodal model

SoulX Singer

SoulX-Singer is a high-fidelity, zero-shot singing voice synthesis model that generates realistic singing voices for unseen singers, with melody-conditioned (F0 contour) and score-conditioned (MIDI) control.

Soul AILab Multimodal Open weights apache-2.0
Open model card ↗
Type
Multimodal
Weights
Open
Downloads
1.5k
Likes
176
Pipeline
text to speech
License
apache-2.0

Model hub

Soul-AILab/SoulX-Singer

Repo
Soul-AILab/SoulX-Singer
Library
huggingface_hub
Access
Public
Technical tags and languages
en zh huggingface_hub text-to-audio music singing-voice-synthesis svs zero-shot text-to-speech
Open on Hugging Face

Papers

1

More from Soul AILab

1

About Soul AILab

1

Since 2016, Soul has grown into a popular AI-native platform for Generation Z. Powered by our proprietary emotional intelligence large model "Soul X" and intelligent relationship-and-content recommendation engine, we transform rich, dynamic, and exclusive public social content into immersive 24/7 experiences that deliver authentic emotional fulfillment through flow states.