ReplicateText to videoComing soon

heygen/video-agent

Name: heygen/video-agent
Brand: Replicate

heygen/video-agent is a text to video tool from Replicate that runs in the background and returns video. Coming soon: listed with its price, not yet open to runs.

This tool is listed but not yet available to run.

Price pending

Pricing

Price pending.

Limits

Runs: In the background
Returns: video
Longest queue wait: 3600s
Run deadline: 3600s
Largest inline input: 1024 KB
Largest input file: 500 MB
Largest output: 4768 MB
Outputs per run: 16

Input

Field	Kind	Default	Description
`prompt` required	text	—	Text prompt describing the video you want to create. The Video Agent handles avatar selection, scripting, scenes, and editing.
`style_id`	text		Visual style template ID from HeyGen's curated styles. Controls scene composition, pacing, and aesthetics.
`voice_id`	text		Voice ID for narration. If not provided, the Video Agent selects a voice automatically.
`avatar_id`	text		Avatar ID to use. If not provided, the Video Agent selects an appropriate avatar.
`orientation`	text		Video orientation. Must be "landscape" or "portrait". Leave empty to let the Video Agent decide.
`duration_sec`	number (whole) 5 to …	—	Approximate target duration of the video in seconds. Minimum is 5.

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "replicate",
    "model": "heygen/video-agent",
    "input": {
      "prompt": "<prompt>"
    }
  }'