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

Muse Code · Video

How to Use Sync React-1 in Muse Code

Sync React-1 changes dialogue and emotional delivery in existing footage, including facial expressions and head motion. Use it for performance edits in clips up to 15 seconds, with one clearly visible speaker.

Prompts to try with Sync React-1 in Muse Code

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

Use Sync React-1 to revise assets/presenter.mp4 with assets/new-intro.wav. Use the first 10 seconds of each, keep one clearly visible speaker, and change facial expressions without adding head motion.

Sync React-1Muse Code
Try asking
  • Use Sync React-1 on the 8-second character shot in assets/scene.mp4 with assets/dialogue.wav. Make the delivery sad and include head movement; save the result beside the source for review.

  • Use Sync React-1 to make neutral and happy performance tests from assets/ad-shot.mp4 and assets/ad-line.wav. Keep both inputs under 15 seconds and use face mode for both tests.

  • Use Sync React-1 to dub assets/welcome.mp4 with the prepared Spanish recording in assets/welcome-es.wav. Use a 12-second shot with one visible presenter and retain the existing head motion.

  • Use Sync React-1 to revise the 10-second generated character clip in assets/character.mp4 with assets/replacement.wav. Include facial expressions and head movement, then add the result to our video review page.

How to set up Sync React-1 in Muse Code

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

Use Spiral's MCP server

  1. Install Muse Code
    curl -fsSL https://dev.meta.ai/install.sh | bash
  2. Ask Muse to add the server

    Start muse and ask:

    Add the Spiral MCP server at https://api.spiral.ai/mcp
  3. Sign in

    In your terminal, run:

    muse mcp login spiral

Use the Spiral skill

  1. Send Muse Code 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.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Sync React-1

    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/sync-lipsync/react-1",
        "input": {
          "video_url": "https://storage.googleapis.com/falserverless/example_inputs/react_1/input.mp4",
          "audio_url": "https://storage.googleapis.com/falserverless/example_inputs/react_1/input.mp3",
          "emotion": "happy"
        }
      }'

Then paste one of the prompts above: Muse Code finds Sync React-1 on Spiral, shows the price and runs it.

Sync React-1 providers and prices

Spiral runs Sync React-1 through fal. Open a card for today's price, with every fee included.

falVideo
Sync React-1
fal-ai/sync-lipsync/react-1

Settings you can ask for

Sync React-1 works from your video URL and audio URL. Ask Muse Code for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Emotionhappy, sad, angry, disgusted, surprised, or neutral

Emotion prompt for the generation. Currently supports single-word emotions only.

Model modelips, face, or headface

Controls the edit region and movement scope for the model. Available options:

  • lips: Only lipsync using react-1 (minimal facial changes).
  • face: Lipsync + facial expressions without head movements.
  • head: Lipsync + facial expressions + natural talking head movements.
Lipsync modecut_off, loop, bounce, silence, or remapbounce

Lipsync mode when audio and video durations are out of sync.

Temperature0 to 10.5

Controls the expresiveness of the lipsync.

Every API field of Sync React-1 is on its tool page: open its card above.

What can you do with Sync React-1 in Muse Code?

Turn recorded or generated project footage into alternative dialogue performances. An agent can prepare shots within the 15-second limit and organize the results for comparison.

Revise a dramatic line

Pair a filmed shot with a replacement recording to try a different emotional delivery. Keep each performance edit within 15 seconds.

Repair dialogue in a generated scene

Keep an AI-generated shot you like and replace the character's dialogue and facial performance.

Localize a short presenter clip

Use a separately translated recording to match a presenter's mouth movements and expression to the new delivery.

Compare ad performances

Try neutral and happy deliveries of a short spokesperson line, then review which expression fits the message.

Update a training introduction

Replace a short instructor introduction with revised speech while retaining the existing shot and framing.

Create character dialogue tests

Use a video of one clearly visible character to compare facial expressions and head motion for a short line.

Revise a welcome message

Pair an existing presenter recording with new greeting audio to make a short welcome clip with matching facial delivery.

Questions about Sync React-1 in Muse Code

Can Muse Code use Sync React-1?

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Sync React-1 like any built-in tool.

How much does Sync React-1 cost in Muse Code?

Up to $13.00 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 Muse Code plan is separate.

Do I need a fal account to use Sync React-1 in Muse Code?

No. Spiral runs Sync React-1 on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Sync React-1 in Muse Code?

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

Does Muse Code wait while Sync React-1 runs?

Sync React-1 runs in the background. Muse Code starts the run, checks on it and gives you the video when it's ready.

What is Sync React-1 useful for?

Use it to change an actor's delivery after filming or generating a scene. It can revise facial expressions and head motion alongside the dialogue, giving you another performance to review without a reshoot.

How long can a Sync React-1 clip be?

The maximum is 15 seconds. For a longer scene, prepare separate shots that each fit within that limit.

Does Sync React-1 work with AI-generated video?

Yes. It supports filmed footage and AI-generated footage, so you can revise a character's delivery after choosing the shot.

What footage should I choose for Sync React-1?

Choose a shot with one clearly visible speaker and keep the face unobstructed. React-1 does not support occlusion detection for partially hidden faces.

Can Sync React-1 dub speech in another language?

Yes, Sync supports lip sync in all spoken languages. Prepare the translation and translated recording separately, then use that recording to drive the performance.

Get started

Start using Sync React-1 in Muse Code

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

Paste this into Muse Code:

Set up Muse Code

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