[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [LatentSync](https://spiral.ai/integrations/chatgpt/latentsync)

# How to Use LatentSync in ChatGPT

LatentSync matches a recorded speaker's mouth movements to replacement speech for dubbing and dialogue corrections. It edits existing footage while aiming to preserve the speaker's identity and head pose.

|  |  |
| --- | --- |
| Model | LatentSync |
| Available through | fal |
| Category | Video |
| Price | Up to $0.39 per run at the default inputs for 60 seconds of input. |
| Returns | video |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with LatentSync in ChatGPT

- Use LatentSync to match this presenter video to my replacement narration. Show me the result for a mouth-timing review.
- Use LatentSync to match this animated dialogue shot to the revised voice recording. Help me check the lips and teeth before I approve it.
- Use LatentSync to create two edits of this clip, one with guidance at 1 and another at 1.5. Compare speech alignment and visible jitter.
- Use LatentSync to dub this 10-second instructor clip with the translated recording. Prepare it as a review cut for a fluent speaker.
- Use LatentSync to replace the spoken line in this spokesperson clip with my corrected recording. Help me compare facial stability with the original.

## How to set up LatentSync in ChatGPT

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

### Use the ChatGPT connector

1. **Add a custom MCP server**: In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **Sign in to Spiral and approve**: Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.

### Use the Spiral skill

1. **Send ChatGPT 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 LatentSync**: 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/latentsync",
    "input": {
      "video_url": "https://fal.media/files/koala/8teUPbRRMtAUTORDvqy0l.mp4",
      "audio_url": "https://fal.media/files/lion/vyFWygmZsIZlUO4s0nr2n.wav"
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds LatentSync on Spiral, shows the price and runs it.

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

## LatentSync tools and prices

- [LatentSync](https://spiral.ai/tools/fal/fal-ai/latentsync) (fal): $0.0065 per second.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| guidance_scale | 1 to 2 | 1 | Guidance scale for the model inference |
| seed |  | — | Random seed for generation. If None, a random seed will be used. |
| loop_mode | pingpong, loop | — | Video loop mode when audio is longer than video. Options: pingpong, loop |

## What can you do with LatentSync in ChatGPT?

Create dubbed presenter clips and revised character dialogue from existing footage with LatentSync. A chat app can help you compare edits and decide whether stronger synchronization is worth any visible distortion.

### Dub a presenter clip

Match an existing presenter shot to a recorded translation. Review the mouth timing against the translated speech before editing the result into the finished video.

### Correct a spoken line

Replace a mispronounced name or outdated sentence in a talking-head segment using a newly recorded line.

### Update training videos

Use existing instructor footage with revised narration for a changed lesson or procedure. Start with a short passage for review.

### Revise animated dialogue

Match an animated character's mouth movements to a replacement voice performance in an existing dialogue shot.

### Prepare spokesperson ad edits

Create separate review cuts of an existing spokesperson video for recorded messages aimed at different audiences.

### Build language lesson clips

Pair presenter footage with recorded example phrases for a language lesson. Have a fluent reviewer check the resulting mouth movements.

## Overview

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

## LatentSync in other agents

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

## More ChatGPT guides

- [LTX-2.3 Pro Extend Video](https://spiral.ai/integrations/chatgpt/ltx-2-3-pro-extend-video)
- [LongCat Video Distilled Image to Video 480p](https://spiral.ai/integrations/chatgpt/longcat-video-distilled-image-to-video-480p)
- [LTX Video 0.9.7 Distilled Text to Video](https://spiral.ai/integrations/chatgpt/ltx-video-0-9-7-distilled-text-to-video)
- [LongCat Video Distilled Image to Video 720p](https://spiral.ai/integrations/chatgpt/longcat-video-distilled-image-to-video-720p)
- [LTX Video 0.9.7 Distilled Image to Video](https://spiral.ai/integrations/chatgpt/ltx-video-0-9-7-distilled-image-to-video)
- [LongCat Video Distilled Text to Video 480p](https://spiral.ai/integrations/chatgpt/longcat-video-distilled-text-to-video-480p)

## Questions about LatentSync in ChatGPT

**Can ChatGPT use LatentSync?**

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

**How much does LatentSync cost in ChatGPT?**

Up to $0.39 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 ChatGPT plan is separate.

**Do I need a fal account to use LatentSync in ChatGPT?**

No. Spiral runs LatentSync on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up LatentSync in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

**Does ChatGPT wait while LatentSync runs?**

LatentSync runs in the background. ChatGPT starts the run, checks on it and gives you the video when it's ready.

**What is LatentSync best used for?**

Use LatentSync to match a recorded speaker's mouth to replacement dialogue. Dubbing, corrected narration, and updated presenter clips are practical starting points.

**Can LatentSync work with animated characters?**

Yes. LatentSync supports both real people and animated characters in existing footage; try a short dialogue shot before processing a longer scene.

**Why can stronger lip synchronization make the video look worse?**

Higher guidance can improve mouth-to-audio alignment while introducing distortion or jitter. Increase it gradually and compare both timing and facial stability.

**Does LatentSync support Chinese speech?**

ByteDance specifically improved Chinese-video performance in LatentSync 1.5 by adding Chinese training data. For Chinese dialogue, test a representative passage rather than assuming identical results across releases.

**What does the published 512 by 512 resolution mean?**

ByteDance describes 512 by 512 as the training resolution for LatentSync 1.6, introduced to address blurry teeth and lips. Treat that figure as release-specific training information when planning output quality.

