Helping Everyone To Unleash
Our AI Research
![](https://cdn.lamucal.com/public/static/img/about/spec1.webp)
Multilingual Text-to-Audio Alignment
End-to-end automatic text-to-audio alignment for multiple languages
![](https://cdn.lamucal.com/public/static/img/about/spec2.webp)
Precision Audio Fingerprinting for Music Recognition
High-precision, high-efficiency audio fingerprinting model, can be used for music recognition, audio retrieval, automated tagging, and other fields.
![](https://cdn.lamucal.com/public/static/img/about/spec3.webp)
AudioFlux: Library for Music Analysis & Retrieval
AudioFlux: a library for audio and music analysis, feature extraction, music-information-retrieval
![](https://cdn.lamucal.com/public/static/img/about/spec4.webp)
Real-time Audio Source Separation with U-Net
U-Net for constructing sparse masks, achieve real-time audio source separation.
Want to join?
Contact us here