Dictate in any app · AI chat

Voice typing in Midjourney

Image prompts are dense descriptive writing squeezed into one line. With Typally you hold a hotkey, speak, and the text lands in Midjourney exactly where your cursor was.

Disclosure: Typally is our product. We have tried to describe what Midjourney already does without talking you out of using it.
Dictate into Midjourney Free forever for 100 minutes a month — no card, no countdown.
Try Typally free

In short

  • Midjourney's own dictation: None. Prompts are typed into Discord or the web interface.
  • What Typally does instead: behaves like a keyboard, so it reaches parts of Midjourney a built-in feature would not.
  • Best used for: image prompts

Does Midjourney have built-in dictation?

None. Prompts are typed into Discord or the web interface.

Why dictate in Midjourney at all?

A good image prompt describes subject, composition, lighting, style and mood. Typing all of that is tedious, so people write four words, get something generic, and iterate twenty times instead.

In practice people use it for: Image prompts, describing a scene fully, iteration notes, and keeping a record of what worked.

How to dictate in Midjourney

You do not configure anything in Midjourney. The hotkey works wherever your cursor happens to be:

1

Set Typally up once

One install, one sign-in. Nothing else to configure.

2

Click into the right box in Midjourney first

Text goes wherever Midjourney has focus. One click first saves undoing a paragraph in the wrong box.

3

Press and speak

Hold, talk, release. Long passages are fine.

4

Read it before you move on

Prompt parameters use double dashes and precise syntax. Dictate the description and add parameters by hand.

What Typally adds in Midjourney

Typally types into the prompt box, so describing subject, lighting, composition and mood costs about as long as saying it. That detail is what typed prompts consistently omit, and it is the difference between twenty iterations and two. Add the double-dash parameters by hand — those are syntax, not description.

What this looks like in practice

Someone stuck iterating on a generic-looking scene describes it out loud instead: the time of day, where the light comes from, what the camera is doing, what mood it should carry. The second generation is close enough to use.

One habit that makes it work better

Describe the picture as if to someone who has to paint it. Speaking naturally produces the lighting and composition detail that typed prompts omit.

What to watch out for in Midjourney

Prompt parameters use double dashes and precise syntax. Dictate the description and add parameters by hand.

Frequently asked questions

Does Midjourney have voice input?

No. Prompts are typed, whether in Discord or the web interface.

Do longer image prompts work better?

More specific descriptions generally give you more control. Whether longer is better depends on what you are after.

Can I dictate parameters like aspect ratio?

Those are symbol-based flags — type them.

Try it in Midjourney

You can try this on the free plan — 100 minutes a month, no card, no trial countdown.

Try Typally free

Also dictate in: ElevenLabs · Runway · Canva · see all apps