How to Use Sync-3 Avatar in Muse Code
Sync-3 Avatar turns a portrait or illustrated face into a talking video driven by your audio. Unlike Sync-3 Lipsync, it creates the facial motion from a still image, and the video's length matches the audio.
Prompts to try with Sync-3 Avatar in Muse Code
Copy an example into Muse Code, or ask in your own words.
Use Sync-3 Avatar with assets/instructor.png and assets/lesson-intro.wav to create a talking introduction. Check that the result follows the recording's duration.
Use Sync-3 Avatar to animate assets/guide-portrait.png with each approved welcome recording in assets/greetings. Keep each output paired with its recording.
Make a talking-head video with Sync-3 Avatar from this headshot and this 20-second voiceover. Save the result in ./assets.
Create a 15-second founder intro with Sync-3 Avatar using the photo and script I attach.
Turn this audio clip into a lip-synced avatar video with Sync-3 Avatar.
How to set up Sync-3 Avatar in Muse Code
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Install Muse Code
curl -fsSL https://dev.meta.ai/install.sh | bash
- Ask Muse to add the server
Start muse and ask:
Add the Spiral MCP server at https://api.spiral.ai/mcp
- Sign in
In your terminal, run:
muse mcp login spiral
Use the Spiral skill
- Send Muse Code this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run Sync-3 Avatar
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/v3/image-to-video", "input": { "image_url": "https://storage.googleapis.com/falserverless/example_inputs/echo-mimic-input-image.png", "audio_url": "https://fal.media/files/lion/vyFWygmZsIZlUO4s0nr2n.wav" } }'
Then paste one of the prompts above: Muse Code finds Sync-3 Avatar on Spiral, shows the price and runs it.
Sync-3 Avatar providers and prices
Spiral runs Sync-3 Avatar through fal. Open a card for today's price, with every fee included.
What can you do with Sync-3 Avatar in Muse Code?
Create talking-presenter assets for onboarding, lessons, and product explanations. Your coding agent can pair project media with finished narration and organize the results for 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.
Illustrated character dialogue
Give an illustrated portrait a speaking performance that follows a supplied voice recording.
Portrait-based announcements
Turn a headshot and an announcement recording into a talking video whose length follows the audio.
More on Sync-3 Avatar and Muse Code
Overview
Sync-3 Avatar in other agents
Questions about Sync-3 Avatar in Muse Code
Can Muse Code use Sync-3 Avatar?
Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Sync-3 Avatar like any built-in tool.
How much does Sync-3 Avatar cost in Muse Code?
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 Muse Code plan is separate.
Do I need a fal account to use Sync-3 Avatar in Muse Code?
No. Spiral runs Sync-3 Avatar 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-3 Avatar 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-3 Avatar runs?
Sync-3 Avatar runs in the background. Muse Code 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.
Start using Sync-3 Avatar 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 https://spiral.ai/SKILL.md


