Skip to content
Docs
Docs

Talking with the Assistant

The Composer's modes (Ask, Image, Video and Audio), talking an idea through with the Assistant, its prompt cards, and each image's own conversation in its editor.

Markdown

The Composer, the prompt at the bottom of a Canvas (and of a Space, see The Space’s Composer), has a mode. Its button sits at the start of the prompt and says the mode you’re in, by its icon and its name. Press it to choose another:

  • Ask (the sparkle) talks with the Assistant. It’s where you start.
  • Image makes an image from what you type, straight away (see Making images).
  • Video makes a video, straight away (see Making videos).
  • Audio opens a menu of its three jobs, Voice-over, Music and Sound effect, each making that kind of sound straight away (see Making audio).

The Composer always opens in Ask, where each reply uses a little of your usage, charged for what it read and wrote (see Usage). Image, Video and Audio’s jobs are for one prompt: once you send, the Composer goes back to Ask. If what you sent is refused, it comes back in its mode, with why. Settings (the sliders button) offers Auto (the default), OpenAI or Claude to answer you. Your choice is remembered in this browser. If the one you chose isn’t available, the Assistant says so rather than using the other; Auto always uses what’s available. Image, Video and Audio’s jobs have their own model menu, and show what sending will cost as the cost meter, because sending there makes something.

The send button is an arrow; the mode button says the mode, and the prompt’s placeholder follows it (“Ask anything…”, “Describe an image to make…”). Hover the arrow to see what it will do: Go (in Ask), Make image, Make video, Make voice-over, Make music or Make sound effect. A prompt, or a message in Ask, can be up to 4,000 characters; a voice-over’s words up to 5,000. Near that, a count shows beside the arrow; over it, the arrow waits until you shorten what you wrote.

On a phone

On a phone, the Assistant waits at the foot of Home and of a Space: Ask or make something in the Space. Tap it to open the Assistant full screen, or tap its microphone to open it listening. It’s the same Assistant, Composer and conversation as on a bigger screen. Back to at the top left returns to where you were. Beside Assistant is where it works: in a Space, tap it to choose another Space, which opens with its Assistant open too. On a Canvas, Ask about this Page opens it (see On a phone). The Composer stays above the keyboard while you type.

What it made shows as a card: tap the picture or Edit to open it in the image editor (quick edit, on a phone), Use as reference to add it to the Composer, Animate to make a video from it (the Composer in Video, with it as the first frame) or Download to save it. Plans it proposes are approved, discarded or undone on their card, as on a bigger screen. Opening a new image or video from a Space’s Assets opens the Assistant too.

Stop

While something you started from the Composer is still running (a reply being written, or images and videos being made), the send button becomes Stop. Stop stops all of it at once:

  • The reply ends where it is, marked Stopped. Anything it was about to make or change isn’t done. You’re charged only for what it had used, if anything.
  • Every image and video you started there that is still being made is cancelled, and its place on the Canvas goes. A stopped image or video costs you nothing, as if it had failed. Where the model can be stopped, it is; where it can’t, whatever it makes afterwards is thrown away, never placed or charged. One that had already finished before you pressed Stop is kept, and charged as usual.

Start writing your next prompt while something runs and the send button comes back, with Stop beside it as a square. What you started before reloading the page carries on: cancel it from its own place on the Canvas or in the conversation.

Speaking a prompt

You can speak instead of typing, in every mode and every Composer. Press the microphone, just left of the send button. The first time, your browser asks whether Otherspace may use your microphone.

While it listens, the microphone turns red and pulses, and an empty prompt says Listening…. Your words appear in the prompt as you say them. They go in where your cursor is, and what you’d already typed stays. A word may change as the browser works out what you said, then it settles.

Nothing is sent by itself: read what it heard, change it if you like, then send. Press the microphone again or Esc to stop listening. A pause to think doesn’t stop it: it keeps listening until about 20 seconds pass with nothing said, or after 5 minutes, and then says so. It also stops when you type, send, switch mode or leave the page. Sending while it listens sends what’s in the prompt.

If it can’t listen, the Composer says why, below the prompt: the microphone isn’t allowed (allow it from the icon at the start of your browser’s address bar), there’s no microphone, or the connection to speech recognition was lost.

It uses your browser’s own speech recognition, in your browser’s language, so it works in Chrome, Edge and Safari (including on iPad and iPhone), and on Android in Chrome. Firefox and the desktop app can’t turn speech into text yet: there, pressing the microphone says so. Speaking costs nothing. Your browser’s maker processes the audio to recognise it (Google for Chrome, Microsoft for Edge, Apple for Safari). Otherspace never receives or keeps the audio, only the words in your prompt (see the Privacy Notice).

Asking

In Ask, write to the Assistant as you would to a person: “I’m thinking of a poster for a jazz night”, “How could we make this more cinematic?”. The moment you send, a bubble opens just above the Composer with Thinking…, and the reply appears in it as it’s written.

The bubble stays while the reply is being written, and while your pointer is on it. If it has a prompt card to use, or asks you something, it stays until you dismiss it (×) or ask something else. Otherwise it goes when you click elsewhere, or after a little while. Show reply brings it back.

Open conversation (the arrows at its top) docks the Assistant right with the whole conversation. Docking the Composer right does the same. Nothing is lost when a bubble goes: every message is kept in the conversation.

Where you put the Composer is where it stays, everywhere: docked right or floating at the bottom, it’s the same on a Canvas, in an image’s editor, and in a Space. Floating, it sits in the same place in the window in each. Docked, drag the Assistant’s left edge to make it wider or narrower, from 320 pixels up to half the window; the handle that moves it sits halfway down, just outside its left edge. Your choices are remembered in this browser.

The Assistant works out what you mean:

  • A question or an idea gets an answer, ideas, or one short question back.
  • A suggestion comes as a prompt card: the prompt it would send, and whether it’s an image, a video, or audio (a voice-over, music or a sound effect, with what it chose for it, see Making audio). Use puts the prompt in the Composer, in that mode, for you to change and send. Make it makes it as it is. A card is made once, and then shows that it was made.
  • A request to make something that you’ve sent from Ask is checked first. Words that clearly ask for an image or a video (“Create an image of…”, “Make a video of waves”) get Did you want to create an image? (or a video) straight back, with your words as a prompt card: Make it makes it, and Use switches to Image or Video with the prompt, to choose its model and settings first. This reply is free: no model is asked. While you’re typing such words in Ask, the Composer already offers Switch to Image (or Video) above the prompt.
  • Anything else the Assistant reads as a clear request (“Make this into a video”, “Make a voice-over that says…”) is made straight away, with no “are you sure?”. It’s priced and charged like anything you make in Image, Video or Audio.

If you’re not sure the Assistant will read you right, ask. When it’s unsure, it proposes rather than making.

What’s made from the conversation appears there with its progress and result, and on the Canvas as usual. So do the images, videos and audio you make in Image, Video or Audio’s modes. A sound plays in the conversation: press play on it. The Canvas’s conversation also shows what was made on the Canvas before you started talking, and what the editor makes.

Each Page of a Canvas has its own conversation. Switching Page shows that Page’s, and a new Page starts with an empty one. The Assistant knows what’s on the Page you’re looking at, and what it changes, it changes there. What you were writing in the Composer, and the references you’d chosen, stay as you switch Page: collect references on one Page and make on another, and the result lands on the Page you’re on. Conversations from before Pages had their own are on each Canvas’s first Page. Deleting a Page deletes its conversation with it.

Working from images

Images you’ve chosen with Use as reference, dragged onto the Composer from the Canvas or the library, or pasted into it, are sent with what you ask, named as the Composer shows them (Image 1, Image 2). The Assistant looks at them, so you can ask “I need a prompt to make something like this” and get one straight away. Once your message is sent they’re let go, ready for the next one. To show the Assistant what’s wrong, take a screenshot and paste it into the prompt (Ctrl/⌘ + V): it’s added as a reference, like a dragged image, in Ask, Image and Video. It shows in the Composer straight away, faded while it’s being stored, and you can send once it’s ready. If it can’t be used (too many images for the model, say), the Composer says why. A pasted image is kept only as a reference: it isn’t added to your assets or placed on the Canvas, and one you never send is removed after 30 days. Pasting text still pastes text. What the Assistant proposes or makes from that message is made with them, and Use puts them back in the prompt along with the card’s prompt. Ask it to change a prompt it wrote (“make the sky blue instead”) and the new prompt is made with the same images, even though you didn’t attach them again. Each card shows the images it’s made with, numbered as the Composer numbers them, so you can see what Make it will send. Ask for something different and it’s made without them. If one of those images no longer exists, the card says so, and nothing is made until you choose Make it. In an image’s editor, the image itself is what the conversation is about; references are the other images you’ve chosen.

Seeing and changing the Canvas

The Assistant knows what’s on the Canvas: every image, video, shape, note, text and frame, what it says, and how each image was made. It knows what you’ve selected, so “make this one blue” works. To keep replies quick, it looks only as far as your question needs:

  • When you ask about layout, or several things (“line these up”, “put a note next to the photo”), it also sees what’s around you, where everything is, and a picture of your view.
  • When you ask about everything (“tidy up the whole canvas”), it sees the whole Canvas.
  • It can also look further, or closer at particular images, whenever it needs to.

Ask it to change the Canvas and it does, straight away:

  • Add shapes (rectangles and ellipses, with a fill, outline and words), text, sticky notes and frames.
  • Arrange: move, resize, line up, space out and group things.
  • Select things for you (“select all the cat pictures”).
  • Delete things. A deletion always asks first: Delete, or Keep to leave things as they are.

Each change shows in the conversation as it’s done, with Undo to put things back as they were. Undo works as long as nothing it changed has been changed again since. It’s also one step of the Canvas’s own undo (Ctrl+Z), and everyone on the Canvas sees it at once. Only the Canvas’s own conversation changes the Canvas: an image’s conversation in its editor can look at it, but not change it.

Organising the library

In a Space, on a Canvas or on a reference’s page, ask the Assistant to organise the Space’s library and it does it, rather than telling you how:

  • “Create a new folder called Jax.”
  • “Move all images of @character-jax into a Jax folder.” It finds a reference’s own pictures, videos and documents by itself.
  • “Rename this folder to Characters”, “Rename the hero image”, or “Put the old sketches in Trash”.

It finds Assets by name, kind and folder, and moves many at once. For something that takes several steps, such as “Create a folder for each Page in this Canvas and organise its images”, it looks at what’s there first, then shows you one plan: the folders it will make and what goes in each. Do it carries out the whole plan, and one Undo puts it all back. Discard leaves everything as it was. An Asset can only be in one folder, so when an image is on more than one Page, the plan files it with the first and tells you so. Each change shows in the conversation as it’s done, with Undo: a move puts every Asset back where it was, and a new folder is removed again while nothing has been put in it. Filing an Asset only changes where it’s kept, so every Canvas and reference that uses it is unchanged. It can move things to Trash when you ask (restorable for 30 days), and never deletes anything for good. It does only what your role in the Space allows: someone who can only view it gets an answer, but nothing changes.

Editing documents and references

Anywhere in a Space, ask the Assistant to change a document or a reference, for example “Update the primary document for @product-the-lakes-boundless based on its reference images”, and it reads the document, looks at the reference’s pictures if it needs to, and proposes the edit. The proposal shows the changed lines and which document it’s for. Apply saves it, Discard leaves it as it was, and nothing changes until you choose. If the document changed since it was read, the edit isn’t applied and it says so, so nothing you wrote is overwritten. Publishing a reference’s new version is still yours to do. From a Space or a reference’s page it edits documents of up to about 6,000 characters whole; for longer ones, open the document and ask there.

Making, and what was made

While an image or video is being made, the conversation shows its shape, then its picture once it’s ready. Cancel stops just that one (Stop in the Composer stops everything running): you’re never charged for it, and its place on the Canvas goes. On a Canvas, a node still being made has Cancel in its menu too (right-click it, or press and hold). An image the Assistant made opens in its editor when you click it.

Hover a message (on a touch screen, they’re always there) to Copy it, or Reuse prompt to put what you said back in the Composer, in the mode you said it in, with the images it was sent with. A proposed prompt has Copy beside Use. Images in the conversation have Use as reference, to add them to what you send next.

An image or video’s Metadata (right-click it on the Canvas) shows the prompt that made it, with Reuse prompt: the prompt goes back in the Composer, with the model it was made with (if you chose one) and the images it was made from. Reuse prompt is also in its menu on the Canvas (right-click it, or press and hold it on a touch screen), beside Metadata, for anything the Assistant made.

Paste a prompt on its own into Ask (one that made something before, say), and the Assistant offers to make it, as a card with Make it, in the medium it describes. Asked to rewrite a prompt you’ve pasted, it proposes the new one: nothing is made until you choose Make it.

An image’s own conversation

Open an image in its editor and the Assistant is there with that image’s own conversation, docked or floating as you last left the Composer. Docked, the editor makes room for it. The Assistant can see the image as it is now, and knows how it was made. Ask it about the image (“What would make this moodier?”), use its cards, or switch to Image to change the image now, or to Video to animate it. A video is placed beside the image on the Canvas.

Ask it to change the image and it does, using the editor’s own tools:

  • Remove the background, delete a mask or turn it off and on, split a layer into its subject and background, and show or hide a layer are done straight away.
  • Relight, Upscale and extending the image to another shape (“make it widescreen”, which fills the new areas) cost money, so they ask first, with their cost on the meter: press Relight, Upscale or Fill to make it, or Not now to leave the image as it is.
  • A change described in words (“make the jacket red”) edits the image, or just the regions you’ve drawn, as Image mode would.

The Assistant knows the image’s layers, so “hide the relit layer” works. If you don’t name one, it uses the layer you’ve chosen, or else the picture itself. Each change shows in the conversation as it’s done. Undo it in the editor (Ctrl+Z), as you would any change there.

Each image keeps its own conversation. Close the editor and open it again, even days later, and its conversation is there. It’s the same conversation wherever you open the image: from a Canvas, from the Space’s library, or by its own address, and even when the image is on several Canvases. Other images’ conversations, and the Canvas’s, are kept apart. An image made from another (a change made beside it) starts a conversation of its own.

A document has its own conversation too, on its page: ask about it, or for a change to review before it’s saved (see Asking the Assistant about a document).

In a Space, the Composer talks in the Space’s own conversation. Every conversation in a Space knows the Space and its newest images and videos.

On Home, the Composer talks in your own conversation in that Organisation, which only you see. It knows your Spaces, not what’s in them: ask it which Spaces you have or who shared them with you, to open one, or to create one. To make something from Home, you choose the Space it goes into (see Asking on Home).

Limits

Everyone who can edit a Canvas can talk with the Assistant there and sees its conversations. People who can only view it see no Assistant, and the same is true of a document. Everyone in an Organisation, Guests too, can ask on its Home.

Each reply uses a little of your usage, at the price of the model that answers (see the price before you send). You can send up to 300 messages a day. Once they’re used, the Assistant says it’s back tomorrow.

Not available yet: 3D.