Auribus
Auribus is an AI-powered audio plugin that generates realistic vocal doubles and harmonies from a single lead vocal performance. The plugin lets producers drag and drop audio from their DAW, audition different AI-singer models, and convert tracks with octave, third, and fifth harmony options. It is built on an ethical model where the professional vocalists whose voices are used are compensated for their contributions.
- Music Technology
- Artificial Intelligence
- Creator / Creative Economy
- Software Only
Funding
Funding not disclosed
Founders
Founder details are not available yet.
Product
Problem
Music producers often need vocal doubles and harmonies to thicken and enrich a lead vocal, but recording additional takes requires access to singers, studio time, and budget. Traditional pitch-shifting and formant-based effects sound processed and lack the natural inflection, vibrato, and performance variance of a real vocalist, limiting their usefulness in professional mixes.
Solution
Auribus provides an AI-powered audio plugin that generates realistic vocal doubles and harmonies from a single lead vocal performance. The plugin can transform a single take into multiple distinct vocal parts, including octave doubles and three-part harmonies, while preserving the nuance and expressiveness of the original performance. Users can quickly audition different AI-singer models, octave choices, and harmony arrangements in real time to find the right sound for a session. The AI models are trained on professional vocalists who are compensated for their contributions, making the tool an ethical alternative to unlicensed voice synthesis. The plugin is designed for use across the entire music production workflow, from early demo writing to final mixing and vocal production.
Target Audience
Primary users are music producers, mixing and mastering engineers, songwriters, and composers working in DAW-based production environments who need fast, realistic vocal doubles and harmonies for demos or final mixes.
Features
- AI-singer models that reproduce natural inflection, vibrato, and pitch variance from the reference performance
- Drag-and-drop workflow directly from a DAW into the plugin, with converted tracks dragged back into the session
- Instant auditioning of different AI voices, octaves, and harmonies with a preview function before conversion
- Alternative versions of every converted track on paid plans, including Higher & Lower Octaves, Thirds & Fifths
- Real-time performance compatible with professional mixing workflows, from demo to final production
- Ethical AI voice generation that properly compensates the vocalists whose voices are used
- Custom voice model creation available on Standard and Premium plans, with up to 6 requests on Premium