AI / Model series
A speech-to-speech model. Voice in, voice out, without the detour through text, and one of the more developed ideas in our pipeline.
PICO is built around a single idea: hear speech and answer in speech directly, without converting to text in the middle. That removes the lag and the loss that come from stitching separate speech-to-text and text-to-speech systems together, and makes for conversation that feels immediate.
PICO is still a concept, but it is further along in our thinking than most. The shape of the model, and what it needs to do, are clearer here than in our earlier-stage series.
Models
First model in the series
The first speech-to-speech model in the series. A concept, but a more developed one.
PICO-1 exists as a design and a direction. We are sharing it at the stage where the idea is solid and the build is not yet underway.
