Spiral gives your agent every tool with one account. Browse the tools →

Hermes · VideoReleased 2026-10-15

How to Use OmniHuman 2.0 in Hermes

OmniHuman 2.0 turns a portrait and recorded speech or singing into a video with matching expressions and gestures. Its five-minute limit suits lessons, songs, and presenter segments that need more than a short talking clip.

Prompts to try with OmniHuman 2.0 in Hermes

Copy an example into Hermes, or ask in your own words.

Each Monday, use OmniHuman 2.0 to turn the approved presenter portrait and that week's 60-second recording into a spoken update. Keep the camera steady and direct a calm, welcoming delivery.

OmniHuman 2.0Hermes
Try asking
  • When a new lesson recording is approved, use OmniHuman 2.0 with the instructor portrait to make its presenter segment. Process recordings from 4 seconds to five minutes, with patient speech and small gestures.

  • Each Friday, use OmniHuman 2.0 with the host portrait and the selected 30-second podcast excerpt. Direct a thoughtful expression and keep the host visible throughout.

  • For each approved 45-second song preview, use OmniHuman 2.0 with the singer portrait. Direct expressive singing with a steady camera and restrained body movement.

  • Each month, use OmniHuman 2.0 with the illustrated guide and the approved 90-second training introduction. Have the guide speak warmly with occasional nods and a small closing smile.

How to set up OmniHuman 2.0 in Hermes

Pick the way that suits you. Each takes about two minutes.

Use the Spiral skill

  1. Send Hermes this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. 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

  1. Add the server and sign in

    Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.

    hermes mcp add spiral \
      --url https://api.spiral.ai/mcp \
      --auth oauth \
      --connect-timeout 300
  2. Check it

    In a chat that was already open, run /reload-mcp.

    hermes mcp list
    hermes mcp test spiral

Use the Spiral CLI

  1. 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

  1. Create an API key

    In the console, under API keys.

  2. Run OmniHuman 2.0

    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": "bytedance/omnihuman/v2",
        "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: Hermes finds OmniHuman 2.0 on Spiral, shows the price and runs it.

OmniHuman 2.0 providers and prices

Spiral runs OmniHuman 2.0 through fal. Open a card for today's price, with every fee included.

falVideo
OmniHuman v2
bytedance/omnihuman/v2

What can you do with OmniHuman 2.0 in Hermes?

Produce recurring presenter segments from prepared portraits and recordings with OmniHuman 2.0. A scheduled agent can apply consistent performance direction to each new lesson, update, or audio excerpt.

Product explanations

Pair a presenter portrait with a recorded product explanation. Direct a calm delivery and small gestures while the presenter speaks.

Course narration

Turn an instructor image and a lesson recording into a presenter segment. Keep each recording within five minutes.

Singing performances

Animate a singer portrait with a recorded song. Describe the mood and camera movement for the performance.

Podcast excerpts

Give a spoken podcast excerpt a visible performer using a host portrait and the original recording.

Recurring illustrated hosts

Pair an illustrated character with recorded narration for a recurring explainer series. Direct the character's expression and gestures for each episode.

Employee training introductions

Use a trainer portrait and recorded introduction to open a training module with a speaking presenter.

Character performance tests

Try the same character image and recording with different emotional directions. Compare the resulting expressions and movement before choosing a performance.

Questions about OmniHuman 2.0 in Hermes

Can Hermes use OmniHuman 2.0?

Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run OmniHuman 2.0 like any built-in tool.

How much does OmniHuman 2.0 cost in Hermes?

Up to $8.19 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 Hermes plan is separate.

Do I need a fal account to use OmniHuman 2.0 in Hermes?

No. Spiral runs OmniHuman 2.0 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 2.0 in Hermes?

About two minutes: add the server and sign in, then check it.

Does Hermes wait while OmniHuman 2.0 runs?

OmniHuman 2.0 runs in the background. Hermes starts the run, checks on it and gives you the video when it's ready.

How long can an OmniHuman 2.0 video be?

The documented range is 4 to 300 seconds. Plan the recording first, because its length determines the video length.

What resolution does OmniHuman 2.0 produce?

OmniHuman 2.0 produces 720p video. Plan your final edit around that resolution.

Can OmniHuman 2.0 animate singing?

Yes. You can use a portrait and a song recording to create a singing performance, with facial expression and movement following the audio.

What should I put in an OmniHuman 2.0 prompt?

Describe the performance: mood, gestures, scene movement, and camera direction. Put the words you want spoken or sung in the recording.

What camera movement should I avoid?

Avoid directing the performer to leave the frame and return. The face can change when the character reappears.

Get started

Start using OmniHuman 2.0 in Hermes

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Hermes:

Set up Hermes

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options