[Integrations](https://spiral.ai/integrations) › [Google Antigravity](https://spiral.ai/integrations/antigravity) › [H3 Max Lip Sync](https://spiral.ai/integrations/antigravity/h3-max-lip-sync)

# How to Use H3 Max Lip Sync in Google Antigravity

H3 Max Lip Sync turns a portrait and recorded audio into a talking video with synchronized mouth movements. Use it for presenter clips, recorded lessons, and greetings when you already have the spoken words.

|  |  |
| --- | --- |
| Model | H3 Max Lip Sync |
| Available through | fal |
| Category | Video |
| Price | Up to $7.488 per run at the default inputs for 60 seconds of input. `resolution`: 480P $4.68, 768P (default) $7.488, 1080P $14.976, 2K $29.952. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with H3 Max Lip Sync in Google Antigravity

- Use H3 Max Lip Sync with assets/presenter.png and audio/welcome.wav to make a 1080p onboarding clip. Check that the recording lasts at least five seconds and enable transcription guidance for the spoken introduction.
- Use H3 Max Lip Sync to animate portraits in assets/characters with their matching recordings in audio/dialogue. Check image ratios against 0.4 to 2.5, flag recordings shorter than five seconds, and save 768p previews.
- Use H3 Max Lip Sync with assets/tutor.png and audio/fractions.wav to produce a 1080p lesson introduction. Check that the tutor's mouth is visible and use transcription guidance.
- Use H3 Max Lip Sync with assets/singer.png and audio/chorus.wav to make a 10-second, 1080p singing preview. Disable transcription guidance.
- Use H3 Max Lip Sync to make separate 1080p support clips from assets/support-host.png and the recordings in audio/help. Measure each recording first and report any image or audio that falls outside the documented limits.

## How to set up H3 Max Lip Sync in Google Antigravity

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

### Use Spiral's MCP server

1. **Open the MCP config**: * Antigravity App: click Customizations, then Installed. In the MCP Servers section, click Copy Config File Path and open that file. * Antigravity IDE: click … at the top of the agent side panel, select MCP Servers, then Manage MCP Servers › View raw config. * Antigravity CLI: edit `~/.gemini/config/mcp_config.json`.

2. **Add the server**: Add Spiral under `mcpServers`:

```json
{
  "mcpServers": {
    "spiral": {
      "serverUrl": "https://api.spiral.ai/mcp"
    }
  }
}
```

3. **Sign in**: In the Antigravity App, open Customizations › Installed. Under MCP Servers, click Authenticate next to Spiral. Sign in to Spiral, pick the organization and click Authorize. Copy the authorization code the browser shows, paste it into Enter authorization code and click Submit. No API key.

### Use the Spiral skill

1. **Send Google Antigravity 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 the Spiral CLI

1. **Install and sign in**: Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

```bash
npx -y spiral-cli@latest init
```

### Call the Spiral API

1. **Create an API key**: In the console, under API keys.

2. **Run H3 Max Lip Sync**: One request; the result comes back by polling or a webhook.

```bash
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": "minimax/h3-max/lip-sync/image-to-video",
    "input": {
      "image_url": "<image_url>",
      "audio_url": "<audio_url>"
    }
  }'
```

Then paste one of the prompts above: Google Antigravity finds H3 Max Lip Sync on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/antigravity

## H3 Max Lip Sync tools and prices

- [H3 Max Lip Sync Image to Video](https://spiral.ai/tools/fal/minimax/h3-max/lip-sync/image-to-video) (fal): Up to $7.488 per run at the default inputs for 60 seconds of input. `resolution`: 480P $4.68, 768P (default) $7.488, 1080P $14.976, 2K $29.952.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| resolution | 480P, 768P, 1080P, 2K | 768P | Output resolution. Uses the supported aspect ratio nearest the image. |
| enable_transcription |  | false | Transcribe the supplied audio to guide lip synchronization. When disabled, synchronize to the audio without a transcript. |
| seed | 0 to 2147483647 | — | Random seed; selected randomly if omitted. |

## What can you do with H3 Max Lip Sync in Google Antigravity?

Turn project portraits and recorded dialogue into talking assets for onboarding, support, or game previews. A coding agent can check image proportions and audio length before generating clips with H3 Max Lip Sync.

### Product presenters

Pair a presenter portrait with a recorded product explanation to make a talking introduction.

### Customer welcome clips

Reuse one host portrait with separate recorded greetings for new customers.

### Illustrated lesson hosts

Animate a drawn tutor to recorded explanations for vocabulary, math, or study reminders.

### Museum portrait narration

Give a painted portrait a recorded narration for an exhibit or classroom presentation.

### Support answer videos

Turn a brand avatar and a recorded answer into a talking clip explaining one common support issue.

### Singing character previews

Pair a character portrait with a sung passage and disable transcription guidance for the performance.

### Recorded announcement updates

Keep a spokesperson portrait and replace the recording when an event announcement or product message changes.

### Game dialogue previews

Animate character portraits to recorded dialogue to review how spoken lines look before further production.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Google Antigravity guides](https://spiral.ai/integrations/antigravity)

## H3 Max Lip Sync in other agents

- [Amp](https://spiral.ai/integrations/amp/h3-max-lip-sync)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/h3-max-lip-sync)
- [Claude](https://spiral.ai/integrations/claude-desktop/h3-max-lip-sync)
- [Claude Code](https://spiral.ai/integrations/claude-code/h3-max-lip-sync)
- [Cline](https://spiral.ai/integrations/cline/h3-max-lip-sync)
- [Codex](https://spiral.ai/integrations/codex/h3-max-lip-sync)
- [Cursor](https://spiral.ai/integrations/cursor/h3-max-lip-sync)
- [Devin](https://spiral.ai/integrations/devin/h3-max-lip-sync)
- [dots](https://spiral.ai/integrations/dots/h3-max-lip-sync)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/h3-max-lip-sync)
- [Gemini](https://spiral.ai/integrations/gemini/h3-max-lip-sync)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/h3-max-lip-sync)
- [goose](https://spiral.ai/integrations/goose/h3-max-lip-sync)
- [Grok](https://spiral.ai/integrations/grok/h3-max-lip-sync)
- [Grok Build](https://spiral.ai/integrations/grok-build/h3-max-lip-sync)
- [Hermes](https://spiral.ai/integrations/hermes/h3-max-lip-sync)
- [Instinct](https://spiral.ai/integrations/instinct/h3-max-lip-sync)
- [Manus](https://spiral.ai/integrations/manus/h3-max-lip-sync)
- [Muse](https://spiral.ai/integrations/muse/h3-max-lip-sync)
- [Muse Code](https://spiral.ai/integrations/muse-code/h3-max-lip-sync)
- [n8n](https://spiral.ai/integrations/n8n/h3-max-lip-sync)
- [Notion](https://spiral.ai/integrations/notion/h3-max-lip-sync)
- [OpenClaw](https://spiral.ai/integrations/openclaw/h3-max-lip-sync)
- [opencode](https://spiral.ai/integrations/opencode/h3-max-lip-sync)
- [Perplexity](https://spiral.ai/integrations/perplexity/h3-max-lip-sync)
- [Raycast](https://spiral.ai/integrations/raycast/h3-max-lip-sync)
- [VS Code](https://spiral.ai/integrations/vscode/h3-max-lip-sync)
- [Windsurf](https://spiral.ai/integrations/windsurf/h3-max-lip-sync)
- [Zapier](https://spiral.ai/integrations/zapier/h3-max-lip-sync)

## More Google Antigravity guides

- [H3 Max Image to Video](https://spiral.ai/integrations/antigravity/h3-max-image-to-video)
- [H3 Max Reference to Video](https://spiral.ai/integrations/antigravity/h3-max-reference-to-video)
- [H3 Max Extend Video](https://spiral.ai/integrations/antigravity/h3-max-extend-video)
- [H3 Max Reframe Video](https://spiral.ai/integrations/antigravity/h3-max-reframe-video)
- [H3 Max Camera Controls](https://spiral.ai/integrations/antigravity/h3-max-camera-controls)
- [H3 Max Relight](https://spiral.ai/integrations/antigravity/h3-max-relight)

## Questions about H3 Max Lip Sync in Google Antigravity

**Can Google Antigravity use H3 Max Lip Sync?**

Yes. Add Spiral to Google Antigravity as an MCP server, and Google Antigravity can find and run H3 Max Lip Sync like any built-in tool.

**How much does H3 Max Lip Sync cost in Google Antigravity?**

Up to $7.488 per run at the default inputs for 60 seconds of input. `resolution`: 480P $4.68, 768P (default) $7.488, 1080P $14.976, 2K $29.952. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Google Antigravity plan is separate.

**Do I need a fal account to use H3 Max Lip Sync in Google Antigravity?**

No. Spiral runs H3 Max Lip Sync on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up H3 Max Lip Sync in Google Antigravity?**

About two minutes: open the MCP config, then add the server, then sign in.

**Does Google Antigravity wait while H3 Max Lip Sync runs?**

H3 Max Lip Sync runs in the background. Google Antigravity starts the run, checks on it and gives you the video when it's ready.

**Does H3 Max Lip Sync create the voice?**

It uses the audio you supply and animates the portrait to that recording. Prepare the spoken performance before generating the video.

**How long can an H3 Max Lip Sync video be?**

Audio must be at least five seconds long. Current API documentation supports up to 15 minutes and says the video matches the supplied audio duration.

**Can H3 Max Lip Sync animate an illustrated character?**

Yes. It supports photographs, 3D renders, 2D illustrations, and paintings, so a recorded line can drive a drawn presenter or painted portrait.

**What portrait works best?**

Choose a clear face viewed from the front or a three-quarter angle, with the mouth visible. An obscured mouth is a poor starting point for judging lip synchronization.

**Should I use transcription guidance for singing?**

Turn it off for music or singing. For spoken dialogue, transcription guidance uses the recorded words to help shape mouth movements.

