# From sound to tokens

> One second of speech has tens of thousands of numbers. A voice model does not write them one by one.

Acoustics · October 31, 2026 · Pedro Cormann, Founder & Machine Learning Engineer · https://lero.studio/research/en/codec

Predicting the waveform number by number would take tens of thousands of steps per second, and a single number carries almost no meaning. That is why modern voice models work in two layers. A codec compresses the waveform into a short sequence, tens of pieces per second, and can go back. A language model, the same kind of network behind a chatbot, learns to predict the next piece from the text and the previous pieces.

_(Interactive on the page: https://lero.studio/research/en/codec)_

The pieces can be integer codes, like words in a sound vocabulary, stacked from coarse (what is said) to fine (the timbre and the room). Or they can be vectors of real numbers, generated by diffusion. The codec carries no text: it only describes sound.

_(Interactive on the page: https://lero.studio/research/en/codec)_