—

Soul AILab

Soul AILab is an AI-native company in —, based in China. Shown below: 2 models.

AI-native Not profitable Featured: —

Visit website

Figures and classifications reflect imported catalog records, not live company reporting.

Models

SoulX Singer Gen 3 Multimodal

Released 7mo ago

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.
- Singing
- Voice cloning
- Voice matching
- Vocal isolation
SoulX FlashTalk Gen 4 Audio

Released 1y ago

A 14B audio-driven avatar model that delivers high-fidelity lip-synced digital humans in real time, with sub-second startup and 30+ FPS streaming for live content.
- Code explanations
- SEO content
- Music
- Image gradients

soulx-flashhead SoulX-FlashHead: Oracle-guided Generation of Infinite Real-time Streaming Talking Heads [Tan Yu*](https://jia…
SoulX-Singer Official inference code for SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis is a high-fi…

Imported positions; not an independent quality score.