Easier to read with cream paper, a tint, more contrast or larger text? Choose your colours and text, once, for every page.

Free module

Multimodal and voice input

Learn multimodal AI hands on: how images, pages and sound become numbers, prepare inputs, check what a model saw, and judge cost and access.

6 lessons435 min lessonSoftware engineering

The lessons

Each lesson is free to read in full. Create a free account to run its commands in a live lab and to sit its quizzes and tasks.

  1. 1 · Container lab

    How an image becomes numbers

    I can say how an image becomes numbers a model reads, and what size and tiles do to its cost.

    Read the lesson

  2. 2 · Container lab

    How to send an image to a model

    I can build a request that carries an image, and refuse a file that breaks a rule before it is sent.

    Read the lesson

  3. 3 · Container lab

    Reading a page: text and fields

    I can turn a page of text boxes into lines in reading order and pull out its fields with their confidence.

    Read the lesson

  4. 4 · Container lab

    How sound becomes text with times

    I can cut samples into frames and join a timed transcript into lines with stamps.

    Read the lesson

  5. 5 · Container lab

    Checking what a model saw

    I can check each claim in a model's description against known facts and decide whether to accept the reply.

    Read the lesson

  6. 6 · Container lab

    Cost, access and privacy of images and voice

    I can price a day of picture, page and sound inputs and flag the ones that need care.

    Read the lesson

Worked in a real lab

Every lesson of this module is worked in a lab started for you alone. The labs it uses:

Teaching a class? Set this module for your students with a teacher guide, marked assignments and a lab for every student.