How to Use OmniHuman 1.5 in OpenClaw
OmniHuman 1.5 turns a portrait and recorded speech or singing into a character performance. Its gestures and expressions respond to the audio’s meaning and emotion, with text guidance for actions and camera movement.
Prompts to try with OmniHuman 1.5 in OpenClaw
Copy an example into OpenClaw, or ask in your own words.
Every Monday, use OmniHuman 1.5 with the approved presenter portrait and that week's 20-second announcement recording. Create a 1080p speaking clip with a steady camera.
Each morning, use OmniHuman 1.5 with the approved mascot image and the day's 15-second greeting recording. Produce a 720p clip with a friendly gesture.
When a new 40-second lesson recording is approved, use OmniHuman 1.5 with the instructor portrait. Create a 720p clip with restrained gestures.
Every Friday, use OmniHuman 1.5 with the approved singer image and 25-second song preview. Render at 1080p and keep the singer visible.
Each month, use OmniHuman 1.5 with the approved character portrait and 45-second story recording. Create a 720p performance with expressions suited to the reading.
How to set up OmniHuman 1.5 in OpenClaw
Pick the way that suits you. Each takes about two minutes.
Use the Spiral skill
- Send OpenClaw this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use Spiral's MCP server
- Add the server
On the machine that runs OpenClaw's Gateway:
openclaw mcp add spiral \ --url https://api.spiral.ai/mcp \ --transport streamable-http \ --auth oauth
- Sign in
In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.
openclaw mcp login spiral
- Reload and check
A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.
openclaw mcp reload openclaw mcp doctor spiral --probe
Use the Spiral CLI
- Install and sign in
Installs the Spiral CLI, signs you in and adds its skill to your coding agents.
npx -y spiral-cli@latest init
Call the Spiral API
- Create an API key
In the console, under API keys.
- Run OmniHuman 1.5
One request; the result comes back by polling or a webhook.
curl https://api.spiral.ai/v1/runs \ -H "Authorization: Bearer $SPIRAL_API_KEY" \ -H "Content-Type: application/json" \ -H "Idempotency-Key: $(uuidgen)" \ -d '{ "provider": "fal", "model": "fal-ai/bytedance/omnihuman/v1.5", "input": { "image_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_image.png", "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/omnihuman_v15_input_audio.mp3" } }'
Then paste one of the prompts above: OpenClaw finds OmniHuman 1.5 on Spiral, shows the price and runs it.
OmniHuman 1.5 providers and prices
Spiral runs OmniHuman 1.5 through fal. Open a card for today's price, with every fee included.
Settings you can ask for
OmniHuman 1.5 works from your prompt, image URL, mask URL, and audio URL. Ask OpenClaw for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Turbo mode | on or off | off | Generate a video at a faster rate with a slight quality trade-off. |
| Resolution | 720p or 1080p | 1080p | The resolution of the generated video. Defaults to 1080p. 720p generation is faster and higher in quality. 1080p generation is limited to 30s audio and 720p generation is limited to 60s audio. |
Every API field of Bytedance Omnihuman V1.5 is on its tool page: open its card above.
What can you do with OmniHuman 1.5 in OpenClaw?
Prepare recurring presenter clips from approved portraits and new recordings. OmniHuman 1.5 can support scheduled announcements, lessons, and character updates.
Product explainers
Animate a presenter portrait with a recorded explanation of one product feature.
Short training lessons
Pair an instructor portrait with recorded narration for a focused lesson.
Song excerpts
Turn a singer portrait and a recorded song excerpt into a performance clip.
Game dialogue previews
Animate character artwork with recorded dialogue to review an acting choice before production.
Mascot announcements
Give an illustrated mascot a speaking performance using an announcement recording.
Dramatic monologue tests
Pair a character portrait with an emotional reading to explore expressions and gestures.
Support answer clips
Create presenter videos from a portrait and recordings of frequently requested explanations.
More on OmniHuman 1.5 and OpenClaw
Overview
OmniHuman 1.5 in other agents
Questions about OmniHuman 1.5 in OpenClaw
Can OpenClaw use OmniHuman 1.5?
Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run OmniHuman 1.5 like any built-in tool.
How much does OmniHuman 1.5 cost in OpenClaw?
Up to $12.48 per run at the default inputs for 60 seconds of input. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.
Do I need a fal account to use OmniHuman 1.5 in OpenClaw?
No. Spiral runs OmniHuman 1.5 on its own fal account. You sign in to Spiral once and never paste a key.
How long does it take to set up OmniHuman 1.5 in OpenClaw?
About two minutes: add the server, then sign in, then reload and check.
Does OpenClaw wait while OmniHuman 1.5 runs?
OmniHuman 1.5 runs in the background. OpenClaw starts the run, checks on it and gives you the video when it's ready.
What is OmniHuman 1.5 good at?
It turns a portrait and recorded audio into a speaking or singing performance. Expressions and gestures can follow the meaning and emotion of the recording.
How long can an OmniHuman 1.5 video be?
Keep audio shorter than 30 seconds for 1080p or shorter than 60 seconds for 720p. Choose the resolution before preparing the recording.
Can OmniHuman 1.5 animate illustrated characters?
Yes. ByteDance demonstrates stylized cartoons, anthropomorphic characters, and animals alongside human subjects.
How should I describe actions?
Put actions in sequence with words such as first and then. Keep the character in view, since leaving the frame for a long time and returning can change its appearance.
Which languages can I use for text prompts?
BytePlus lists Chinese, English, Japanese, Korean, Mexican Spanish, and Indonesian. This list describes text-prompt support.
Start using OmniHuman 1.5 in OpenClaw
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into OpenClaw:
set up https://spiral.ai/SKILL.md


