Access

Text → shot → job → video

Text-to-video API. One shot. Five routes.

Turn one filmable prompt into a priced, trackable video job. Pin a model or route by audio, duration, resolution, availability, and maximum cost.

POST /v1/videosestimate first
{
  "mode": "text_to_video",
  "prompt": "A ceramic robot florist...",
  "duration_seconds": 10,
  "aspect_ratio": "16:9",
  "resolution": "720p",
  "audio": "required",
  "route": "cheapest_compatible",
  "max_cost_usd": 0.50
}

Prompt anatomy

Give the camera something visible to do.

Keep the prose about the shot. Keep duration, ratio, resolution, model, audio, callback, and budget in typed API fields.

01

Subject

A ceramic robot florist

02

Action

ties a red ribbon around one bouquet

03

Scene

inside a rain-lit shop at blue hour

04

Camera

slow push from wide shot to medium close-up

05

Finish

soft window light, paper rustle, one bell chime

A Cre8vid prompt direction board shows subject, scene, camera, motion, and sound instructions for text-to-video generation.
Subject → action → scene → camera → finishOriginal Cre8vid prompt study

Text-to-video route prices

Ten seconds from $0.25.

Compare the same duration and output settings. Every rerun is another generated attempt.

RouteFrom10 secondsUse
Wan 3$0.025/s$0.25Lowest listed start
MiniMax H3$0.029/s$0.29Low-cost second family
Kling 3$0.039/s$0.39Controlled motion route
Veo 3.1 Fast$0.049/s$0.49Listed native-audio route
Seedance 2.5$0.069/s$0.69Higher-cost review route
01

Validate

Reject unsupported settings.

02

Estimate

Return route and total.

03

Generate

Create one idempotent job.

04

Deliver

Return output and final cost.

Text-to-video questions

One search. One complete answer.