Skip to the contentAutomation & AI agents
Ami StudioOleksii Zahlukha

Automation & AI agentsEyes and ears — making sense of an image or a sound

Eyes and ears — making sense of an image or a sound

Send a screenshot or a voice note and get back what is in it, in words. The other agents lean on this whenever a person sends something that is not text.

How it's wired

IncomingKeysPrepareAn image?Vision (Gemini)Speech?Hearing (Groq)Result
Eyes and ears8 · 9

Drawn from the live workflow — every node and every arrow is really there. The labels are translated from the originals.

What it is

Send a screenshot or a voice note and get back what is in it, in words. The other agents lean on this whenever a person sends something that is not text.

Nearby work

Back to Automation & AI agents