The generation panel has two text tools: the microphone and the prompt assistant. Both buttons are available in any mode where the model has a text field.
Dictation
The microphone records up to a minute of speech. Recording stops with the Stop and transcribe button or on its own after 60 seconds, then the text is transcribed and appended to the end of the prompt after a space, and what you wrote earlier stays. You do not need to choose a language. The same button is in the Agent chat and in Studio, in the Avatars and Products sections.
A prompt for the model
The assistant is the button with the Write a prompt for the selected model tooltip. It takes the text in the field as the task and writes a full prompt for the selected model from it. Every explicit fact from your text is kept: the character, the action, lines, text in the shot, song lyrics. The assistant does not add a plot, product or event of its own.
| Result type | What the assistant adds |
|---|---|
| Image | Composition, environment, light, palette and materials. |
| Video | Action over time, framing, camera behavior and sound. |
| Music | Style, tempo, instruments, structure and dynamics. |
Settings, references and language
The assistant sees the selected model and its settings: format, duration, resolution, sound, number of outputs. The values of these settings are not carried into the text; the panel controls manage them. Attached references and slot materials also go into the context. If the model requires references like @Image1, a result without them is not inserted.
The model sets the prompt language.
- Most models
- English
- Nano Banana, Qwen Image 3, Seedance
- Interface language
Separately from the assistant, the panel checks the text against the settings. If the prompt says 15 seconds but a different duration is selected, mentions @image2 that is not attached, or describes video while image mode is selected, that place is underlined, and a hint names the mismatch, for example Duration doesn't match the prompt. Clicking the hint fixes the setting. The hint does not block the launch.
Undo, repair and project rules
The finished prompt goes into the field, and a Restore previous prompt button appears: it returns the text and settings to their state before the assistant. If the result does not pass the check, because it came out empty, longer than the model's limit or lost a required reference, the field stays as it was, and a hint names the reason.
The assistant also works from the project media library.
| Button | What it does |
|---|---|
| Repair prompt with AI | On a generation card that the filter rejected or that came back empty: rewrites the original prompt and opens the panel in that generation's mode. |
| Extract prompt | In the finished image viewer, builds a standalone prompt from the content and style of the image. |
The Prompt improvement field in project settings sets standing conditions for every assistant run in this project, for example:
no cartoon look, English text, photorealism
Ways to use it
An idea by voice from a phone
Tap the microphone in the generation panel, say the scene, correct the transcribed text and start the generation.
One line instead of a full prompt
Write the core of the scene and press the assistant: it adds light, framing, camera and motion for the selected model.
FAQ
How long can I speak in one recording?
Up to a minute. After 60 seconds the recording stops and is transcribed on its own. Dictate a long idea in several passes: each part is appended to the end of the prompt.
Do I need to choose a language for dictation?
No, there is no language choice: the recording goes to transcription as is, and the text returns to the prompt field, where you can correct it.
Why do some models have no assistant button?
The assistant appears only when the model's field is a prompt. In voiceover, some avatars and lip-sync, the text goes to the model verbatim, and some models have no prompt field. The microphone stays in these modes.
Why did the assistant write the prompt in English?
The model sets the prompt language. For most models it is English; Nano Banana, Qwen Image 3 and Seedance get the prompt in the interface language.
Can I get my own text back after the assistant?
Yes. The Restore previous prompt button restores the text and settings that were there before it.
