Use the OmniHuman API via RunAPI with a model skill, unified auth, and pay-as-you-go pricing.
curl -X POST https://runapi.ai/api/v1/omnihuman/audio_to_video \
-H "Authorization: Bearer $RUNAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "omnihuman-1.5-subject-detection",
"image_url": "https://cdn.runapi.ai/public/samples/portrait.jpg",
"audio_url": "https://cdn.runapi.ai/public/samples/voice.mp3"
}'import { OmnihumanClient } from "@runapi.ai/omnihuman";
const client = new OmnihumanClient();
const result = await client.audioToVideo.run({
model: "omnihuman-1.5-subject-detection",
image_url: "https://cdn.runapi.ai/public/samples/portrait.jpg",
audio_url: "https://cdn.runapi.ai/public/samples/voice.mp3",
});require "runapi/omnihuman"
client = RunApi::Omnihuman::Client.new
result = client.audio_to_video.run(
model: "omnihuman-1.5-subject-detection",
image_url: "https://cdn.runapi.ai/public/samples/portrait.jpg",
audio_url: "https://cdn.runapi.ai/public/samples/voice.mp3"
)npx skills add runapi-ai/omnihuman -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 cursorOmniHuman generates talking-head video from a source image and driving audio. Helper endpoints can identify human regions and return subject masks that can be passed into the audio-to-video request.
| Endpoint | Resolution | Duration | Price | |
|---|---|---|---|---|
| audio_to_video | 720p, 1080p | — | $0.32 / second |
Prices shown for omnihuman-1.5. Other variants retain their own endpoint pricing.
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.
OmniHuman belongs to the Bytedance catalog on RunAPI and exposes audio-to-video generation plus human-identification and subject-detection helpers through unified API, SDK, CLI, Bruno, and docs surfaces.
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.
Audio-to-video requires a source image URL and a source audio URL. Optional mask URLs, prompt guidance, resolution, fast mode, seed, and callback URL can refine the task.
Human identification analyzes one source image and returns image outputs that identify human regions for review or preprocessing.
Subject detection analyzes one source image and returns mask outputs that can be used as `mask_urls` in an OmniHuman audio-to-video request.
Pass mask URLs when you want stronger subject isolation or when a prior subject-detection task produced masks for the same source image.
OmniHuman audio-to-video supports 720p and 1080p output; 1080p is the default when the request does not specify a resolution.
Pick the cheapest variant that meets your quality bar. Most teams start on the fast variant and graduate to pro for production.