Make an AI character video from text

With Cast you make an AI character video from text by picking or describing a character and typing one line about what happens; Cast expands the line into a full video prompt and renders a vertical 5, 10, 15-second clip with ByteDance Seedance. The first 5-second video is free with no sign-up, and Standard videos cost 52 credits for 5 seconds after that.

The three steps

1. Who: pick a free pack character or describe your own in one sentence (15 credits, four looks to choose from).
2. What: one line of text. Optionally a style, a camera and a vibe.
3. Get it: the video lands in your private feed, usually in about a minute.

What happens to your text

A short line is not enough for a video model, so Cast expands it. A Claude model normally writes the expanded prompt; if that call fails, a built-in template writes it instead. Here is the template's real output for this input, generated by the same code Cast runs:

You type (Malfoid, Dark Fantasy, Selfie / Live, Comedy, 10 s):

reads her hate mail live at breakfast and one letter starts screaming at her

Cast sends to Seedance, with Malfoid's picture as @image1:

Dark fantasy epic, gothic atmosphere, candle and moonlight chiaroscuro, drifting mist and embers, ornate weathered textures, deep jewel-tone shadows, painterly cinematic grandeur with sharp detail on faces and costume, vertical 9:16 frame. Malfoid (@image1): A 19-year-old young woman: very long straight platinum-blonde hair worn loose past the waist with a centre part and soft face-framing strands, pale porcelain skin, grey-green eyes with a heavy-lidded haughty gaze, straight dark-blonde brows, a small straight nose, full pouty lips and a delicate jaw, small silver hoop earrings, slender figure. Wears a black wool school robe with an emerald-green silk-lined hood, a charcoal-grey V-neck knit vest over a crisp white collared shirt, an emerald-and-silver striped tie, a charcoal pleated skirt and sheer black tights. Sneering, proud, secretly soft-hearted. Keep every face, hairstyle and outfit exactly as in the reference images. Action across 10 seconds in 3 quick, readable beats: reads her hate mail live at breakfast and one letter starts screaming at her, each beat landing with clear body movement and expressive faces while hair and fabric swing and the environment reacts. Camera: one continuous take from the character's own phone held at arm's length, front-camera selfie framing, the arm and slight wobble of a real handheld phone, the character talks straight into the lens like a livestream, no cuts. Pacing: a setup beat, a hard pause, then an oversized reaction. Light: bright even daylight, clean saturated colour, no dramatic shadow. Real-time full-speed motion, no slow motion. No on-screen text, subtitles, captions, logos, watermarks or interface overlays. End with action.

It fixes the identity from the reference, sets the camera, pacing and light from your picks, splits the clip into beats, and bans on-screen text. The prompt library shows what longer hand-written prompts look like.

Real results from text

• Malfoid and two friends dance on the feast tableDance to a song · 30s
• Malfoid reads her hate mail livePhone-POV livestream · 30s
• Penny explains how to build a bank from scratchExplainer · 82s

When Cast is not the right tool

• Text-to-video without a character, such as landscapes or product B-roll. Cast is built around characters.
• Precise control over every shot. One line gives you a good clip, not a storyboard.
• Videos with your own uploaded voice or footage.

Comparing tools? See Cast and its alternatives.

Quick answers

How do I turn text into a video of a character?

Pick a character (or describe one in a sentence), type one line about what they do, optionally choose a style, camera and vibe, and tap make. Cast writes the full prompt and renders the video.

Which model turns the text into video?

ByteDance Seedance 2.0 Fast for Standard videos (720p) and Seedance 2.5 for Pro (1080p). A Claude model writes the expanded prompt.

Can I make my own character from text?

Yes. Describe them in words; Cast draws four looks with Midjourney v8.2 for 15 credits and you pick one.

Updated 2026-10-17