Know if a track was AI-generated. And the physical evidence behind it.
VERA™ is the verification and evidence layer for music. It measures the traces a generator leaves in the audio, for when a decision has to hold up.
Book a demo · How VERA compares
IFPI Sweden, Rexius and SYNNK already run on the new standard.
The evidence is already in the audio.
VERA reads the raw audio signal itself. AI generators build sound on a rigid mathematical grid, and that grid leaves a physical trace in the recording. VERA measures those traces and plots them against the reference for the generator that made them.
Model attribution
Identify the generator behind a track by its unique signature.
Stem groups
Measure vocals, drums and other separately to reveal generated parts within a human-made mix.
Flagging a track is the easy part. Showing the evidence is not.
Decisions
Platforms, charts, and rights bodies now act on what they find.
Questions
An artist, a label, or a rights holder asks how you know.
Evidence
The answer has to come from the recording, in a form anyone can read.
Built for the whole team.
Check one track by hand, or connect VERA to your delivery flow. Every result stays on record, and everyone can see it.
Manual verification
Drop your files in to verify multiple tracks by hand.
API
Integrate verification straight into your own ingestion system and send through whatever you need checked.
History
Every analysis stays on record. Search past results, reopen the evidence, and export a report whenever someone needs to see it.
Teams
Seats, roles, and shared results, so every finding lives with the organization rather than with the person who ran it.
A Swedish team with a stubborn idea.
Radar and software engineers, music industry people, and musicians, building the verification tools the next chapter of audio needs.
A few quick questions and answers.
What's next for VERA™?
A lot, and some of it is big. VERA runs on research we do ourselves, and that research is moving fast. More generators are on the way, and each one comes with your plan at no extra cost. Beyond that, we're building things nobody in this field can do yet. Soon a result won't just name the generator. It will show you how that generator relates to the others. It's the most exciting work we've done, and we'll share it as soon as it ships.
Is VERA™ an AI music detector?
Not in the usual sense. As far as we know, every AI music detector on the market today is a classifier. They estimate a probability, usually from a model trained on a lot of audio, and usually across the whole mix at once. VERA is a verification tool, built from measurement methods we made ourselves. We separate the stems, check each one for the known pattern a specific generator leaves behind, and plot what we found against the reference for that generator. There is a number in the report as well, but it measures how closely your track matches that reference, not how likely it is to be AI.
How accurate is VERA™?
Accuracy percentages are a machine-learning measure of how often a model's predictions matched a labeled test set. We measure the recording rather than predicting from it, so the question is different. Is a known generator pattern present in this audio, and can you see it? Every result comes with the measured signature plotted against the reference it was compared with. The figure we watch hardest is how often authentic music gets flagged, because a wrong flag lands on a real creator. Across a large reference set of human-made music, fewer than 0.04% of tracks came back flagged. Read that as a ceiling, not a rate. In customer use to date there are zero confirmed false positives.