Built to be plain about sound.

Sound from words is easy to promise and hard to demonstrate honestly. So we start with what is true: today the maker in AI Audio is a Preview. It synthesises real sound in your browser, in plain code: a robot voice built from formants, music beds from chords, bass and drums, and effects shaped by the word you use. It is real sound, and it is not a voice model.

Around it is the product we are building: voice-overs in English, German and Dutch, music beds with a mood and a length and a seamless loop, sound effects, two-voice dialogue from a script, a history that keeps every run and every take with its settings, a waveform player, variations, collections, uploads, downloads and saving to Geenius OS Media with provenance. Real voice models plug into the same place, and some are connected in code, ready where their keys are set.

What it is, and what it is not#

AI Audio is a library and a maker, in that order. Pro is the library; making sound is Premium and Max, paid in credits. It is not a recording studio and it does not promise a natural human voice today. The interface says which model made each take.

Part of Geenius OS#

AI Audio is one of the external apps of Geenius OS. Its full name is Geenius AI Audio. A Geenius OS plan includes the matching AI Audio plan, and sounds can go to and come from your Geenius OS Media library.

Who makes it#

AVS Media, a small company in Nijmegen, the Netherlands. The imprint has the details. We say what is live, what depends on your setup and what is not offered, and the examples on this site use sample data.