> ## Documentation Index
> Fetch the complete documentation index at: https://docs.tryflowy.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Text Node

> Write prompts, scripts, and notes that feed downstream generations.

export const DemoVideo = ({src, poster, caption, aspectRatio = "16 / 10", className = ""}) => {
  return <figure className={`not-prose my-6 w-full ${className}`}>
      <div className="overflow-hidden rounded-2xl border border-gray-950/10 bg-gray-100 dark:border-white/10 dark:bg-white/5" style={{
    aspectRatio
  }}>
        <video src={src} poster={poster} loop autoPlay muted playsInline className="h-full w-full object-cover" />
      </div>
      {caption && <figcaption className="mt-2 text-center text-sm text-gray-500 dark:text-gray-400">
          {caption}
        </figcaption>}
    </figure>;
};

Text nodes hold the words on your canvas — prompts, scripts, captions, and notes — and feed them into whatever you connect next. Type directly, or give the node an instruction and let it generate or transform the text with AI.

<DemoVideo src="/videos/canvas/node-text.mp4" poster="/images/posters/canvas/node-text.jpg" caption="Writing in a Text node and feeding it into an image generation" />

## Write or generate

Type straight into the content area when you already know what you want to say. For everything else, write an instruction in the prompt bar and click **Run**: draft ad copy, write a voiceover script, punch up a caption, or rewrite existing text in a different tone. The node holds the result, and you can keep editing it by hand afterwards.

You can also connect one image into a Text node and write about it — caption a product shot, describe a generated frame, or turn a moodboard image into a reusable prompt.

## Feed it downstream

A Text node's output can drive nearly every other node on the canvas:

* **Text → Image** — the text becomes prompt context for the generation.
* **Text → Video** or **Text → Flam** — scripts and shot descriptions steer the clip.
* **Text → Audio** — narration scripts, lyrics, and sound descriptions feed voiceover, music, and SFX.
* **Text → Storyboard** — a brief becomes the source material for a full scene plan.
* **Text → Vector** or **Text → 3D** — describe the logo, icon, or model you want.

Because connections carry context automatically, a single well-written Text node can drive several generations at once — connect it to three Image nodes with different settings and compare the results side by side.

<Tip>
  Keep reusable direction in its own Text node — a style description, a brand voice, a recurring character brief — and wire it into every generation that should follow it. Update it once, and every downstream run picks up the change.
</Tip>