[Integrations](https://spiral.ai/integrations) › [dots](https://spiral.ai/integrations/dots) › [Sync-3 Lipsync](https://spiral.ai/integrations/dots/sync-3-lipsync)

# How to Use Sync-3 Lipsync in dots

Sync-3 Lipsync matches an existing video's mouth movements to new speech while preserving the performance. Unlike Sync-3 Avatar, it starts with footage, making it useful for dubbing and replacing dialogue.

|  |  |
| --- | --- |
| Model | Sync-3 Lipsync |
| Available through | fal |
| Category | Video |
| Price | Up to $10.40 per run at the default inputs for 60 seconds of input. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Sync-3 Lipsync in dots

- Each morning, use Sync-3 Lipsync to match newly approved presenter clips with their corresponding localized speech recordings.
- Each day, use Sync-3 Lipsync for approved replacement-dialogue recordings paired with existing footage. Flag noisy or overlapping speech for review first.
- Every Monday at 9am: make a talking-head video with Sync-3 Lipsync from this headshot and this 20-second voiceover.
- Create a 15-second founder intro with Sync-3 Lipsync using the photo and script I attach.
- Turn this audio clip into a lip-synced avatar video with Sync-3 Lipsync.

## How to set up Sync-3 Lipsync in dots

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

### Use the Spiral skill

1. **Send dots 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. **Create an API key**: In the console, open API keys and create a key for your dot. Copy it.

2. **Send your dot this message**: Your dot reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give your dot the key**: When your dot asks for the key, add it where your dot keeps secrets, never in the chat itself.

### 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 Sync-3 Lipsync**: 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": "fal-ai/sync-lipsync/v3",
    "input": {
      "video_url": "https://v3.fal.media/files/tiger/IugLCDJRIoGqvqTa-EJTr_3wg74vCqyNuQ-IiBd77MM_output.mp4",
      "audio_url": "https://fal.media/files/lion/vyFWygmZsIZlUO4s0nr2n.wav"
    }
  }'
```

Then paste one of the prompts above: dots finds Sync-3 Lipsync on Spiral, shows the price and runs it.

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

## Sync-3 Lipsync tools and prices

- [sync-3 Lipsync · Video to Video](https://spiral.ai/tools/fal/fal-ai/sync-lipsync/v3) (fal): $10.40 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| sync_mode | cut_off, loop, bounce, silence, remap | cut_off | Lipsync mode when audio and video durations are out of sync. |
| options |  | — | Additional Sync.so generation options. If options.sync_mode is set, it overrides the top-level sync_mode field. |

## What can you do with Sync-3 Lipsync in dots?

Produce recurring presenter videos from approved visuals and finished recordings. A scheduled agent can apply the same media checks each time and collect results for editorial review.

### Localized training lessons

Match an instructor's footage or portrait to separately prepared narration in each target language.

### Product onboarding

Create a presenter-led explanation from recorded footage or a portrait and a finished voice track.

### Personalized welcome messages

Pair a presenter visual with separately prepared greetings that speak each recipient's name.

### Social explainers

Produce short talking-presenter clips from footage or a portrait, using clear narration without background music.

### Replacement dialogue

Match existing footage to a newly recorded line while retaining the source performance's cadence and expression.

### Dubbed close-ups

Match translated speech to existing close-up or profile footage, then inspect mouth detail before finishing the edit.

## Overview

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

## Sync-3 Lipsync in other agents

- [Amp](https://spiral.ai/integrations/amp/sync-3-lipsync)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/sync-3-lipsync)
- [Claude](https://spiral.ai/integrations/claude-desktop/sync-3-lipsync)
- [Claude Code](https://spiral.ai/integrations/claude-code/sync-3-lipsync)
- [Cline](https://spiral.ai/integrations/cline/sync-3-lipsync)
- [Codex](https://spiral.ai/integrations/codex/sync-3-lipsync)
- [Cursor](https://spiral.ai/integrations/cursor/sync-3-lipsync)
- [Devin](https://spiral.ai/integrations/devin/sync-3-lipsync)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/sync-3-lipsync)
- [Gemini](https://spiral.ai/integrations/gemini/sync-3-lipsync)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/sync-3-lipsync)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/sync-3-lipsync)
- [goose](https://spiral.ai/integrations/goose/sync-3-lipsync)
- [Grok](https://spiral.ai/integrations/grok/sync-3-lipsync)
- [Grok Build](https://spiral.ai/integrations/grok-build/sync-3-lipsync)
- [Hermes](https://spiral.ai/integrations/hermes/sync-3-lipsync)
- [Instinct](https://spiral.ai/integrations/instinct/sync-3-lipsync)
- [Manus](https://spiral.ai/integrations/manus/sync-3-lipsync)
- [Muse](https://spiral.ai/integrations/muse/sync-3-lipsync)
- [Muse Code](https://spiral.ai/integrations/muse-code/sync-3-lipsync)
- [n8n](https://spiral.ai/integrations/n8n/sync-3-lipsync)
- [Notion](https://spiral.ai/integrations/notion/sync-3-lipsync)
- [OpenClaw](https://spiral.ai/integrations/openclaw/sync-3-lipsync)
- [opencode](https://spiral.ai/integrations/opencode/sync-3-lipsync)
- [Perplexity](https://spiral.ai/integrations/perplexity/sync-3-lipsync)
- [Raycast](https://spiral.ai/integrations/raycast/sync-3-lipsync)
- [VS Code](https://spiral.ai/integrations/vscode/sync-3-lipsync)
- [Windsurf](https://spiral.ai/integrations/windsurf/sync-3-lipsync)
- [Zapier](https://spiral.ai/integrations/zapier/sync-3-lipsync)

## More dots guides

- [Sync-3 Avatar](https://spiral.ai/integrations/dots/sync-3-avatar)
- [VEED Avatars Audio to Video](https://spiral.ai/integrations/dots/veed-avatars-audio-to-video)
- [Sync React-1](https://spiral.ai/integrations/dots/sync-react-1)
- [VEED Dubbing Pro](https://spiral.ai/integrations/dots/veed-dubbing-pro)
- [Sync Lipsync 2.0 Pro](https://spiral.ai/integrations/dots/sync-lipsync-2-0-pro)
- [VEED Dubbing Standard](https://spiral.ai/integrations/dots/veed-dubbing-standard)

## Questions about Sync-3 Lipsync in dots

**Can dots use Sync-3 Lipsync?**

Yes. Add Spiral to dots as an MCP server, and dots can find and run Sync-3 Lipsync like any built-in tool.

**How much does Sync-3 Lipsync cost in dots?**

Up to $10.40 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 dots plan is separate.

**Do I need a fal account to use Sync-3 Lipsync in dots?**

You need no fal account. dots uses one Spiral API key for every tool, and Spiral runs Sync-3 Lipsync on its own fal account.

**How long does it take to set up Sync-3 Lipsync in dots?**

About two minutes: create an API key, then send your dot this message, then give your dot the key.

**Does dots wait while Sync-3 Lipsync runs?**

Sync-3 Lipsync runs in the background. dots starts the run, checks on it and gives you the video when it's ready.

**Which languages does Sync-3 support?**

Sync-3 supports lip syncing across more than 95 languages, including English, Hindi, and Japanese. Supply speech already recorded in the language you want viewers to hear.

**What matters most when asking an agent to use Sync-3?**

Identify the visual source and the exact speech track to match. Clear speech and a readable, front-facing face are more useful than a long description of the scene.

**Why might the mouth movements look inaccurate?**

Background music, heavy noise, or overlapping voices can make alignment less reliable. Try an isolated voice track and a source where the face is easy to see.

**What resolution can Sync-3 produce?**

The maker documents native 4K output and support up to 60 fps. Treat those as supported capabilities, rather than a promise that every result will be delivered at that size and frame rate.

**Can I adjust a temperature setting to change the performance?**

Sync-3 sets expressiveness automatically and does not offer temperature as a creative control. Choose the source visual and voice performance carefully.

