Use the HeyGen Video API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/heygen_video/image_to_video \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "heygen-video-1",
"first_frame_image_url": "https://cdn.runapi.ai/public/samples/image.jpg",
"prompt": "Generate a 10-second 1080p product video of a ceramic mug on a sunlit kitchen counter, using the reference image to keep the mug design consistent and adding soft ambient sound."
}'import { HeygenVideoClient } from "@runapi.ai/heygen-video";
const client = new HeygenVideoClient();
const result = await client.imageToVideo.run({
model: "heygen-video-1",
first_frame_image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 10-second 1080p product video of a ceramic mug on a sunlit kitchen counter, using the reference image to keep the mug design consistent and adding soft ambient sound.",
});require "runapi/heygen_video"
client = RunApi::HeygenVideo::Client.new
result = client.image_to_video.run(
model: "heygen-video-1",
first_frame_image_url: "https://cdn.runapi.ai/public/samples/image.jpg",
prompt: "Generate a 10-second 1080p product video of a ceramic mug on a sunlit kitchen counter, using the reference image to keep the mug design consistent and adding soft ambient sound."
)npx skills add runapi-ai/heygen-video -g# Claude Code
claude mcp add runapi -s user -- npx -y @runapi.ai/mcp
# Codex
codex plugin install runapi-mcp@agents
# Cursor / Windsurf / VS Code
npx @runapi.ai/mcp init cursorThe HeyGen Video API (model ID heygen-video-1) generates 5 to 15 second videos with dialogue, ambience, and effects from the same request. Create from a text prompt, animate a first-frame image, or guide generation with reference images, videos, and audio to keep products, people, and places consistent.
| Model ID | heygen-video-1 |
| Provider | HeyGen |
| Modality | video |
| Task type | asynchronous |
| Billing unit | second |
| API endpoint | /api/v1/heygen_video/image_to_video |
| Commercial license | Yes — included via API |
| Catalog status | Operational |
Sign up and generate an API key from the dashboard.
Choose the version that best matches your quality and cost requirements.
Submit your prompt and parameters to the model's documented endpoint.
Poll the task or set a webhook, then download the completed output.
Use one RunAPI model ID for text-to-video, image-to-video, and reference-guided generation. Output runs from 480p to 2K, and reference mode accepts up to 9 images, 3 videos, and 3 audio clips, with at most 12 reference files in total.
A single RunAPI API key unlocks the whole model catalog across all providers. No separate accounts to create, no API keys to rotate per integration, and no credential management overhead. Add a new model to your app by changing one parameter.
Per-call pricing in USD, billed monthly into a single invoice. No subscription tiers, no minimum spend, and failed generations are never charged. The pricing page and check_pricing API show exact costs before you commit to a model.
Typed schemas, parameter constraints, and setup notes are packaged in the model skill so your implementation starts from the right contract. The skill loads into Claude Code, Codex, Gemini CLI, Cursor, and VS Code — your agent knows the correct request shape before you write a line of code.
Send heygen-video-1 as the model value. The text-to-video endpoint takes a prompt and optional reference images, videos, or audio; the image-to-video endpoint takes a prompt and a first-frame image.
Use a text prompt, a first-frame image, or reference images, videos, and audio clips. Outputs support 5 to 15 seconds at 480p, 768p, 1080p, or 2K, and include generated sound.
Yes. Every clip includes generated dialogue, ambience, and effects from the same request.
Billing is per second of video. The pricing table on this page lists the current rate for each resolution and input type, and failed generations are not charged.
No. HeyGen Video is HeyGen's general video model and builds the whole scene, sound included, from a prompt or images. Talking-avatar videos made from a script and a chosen voice come from HeyGen's separate avatar API, which RunAPI does not offer.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.