How to Use Sync Lipsync 2.0 in Claude
Sync Lipsync 2.0 matches existing talking footage to replacement speech while preserving the speaker’s style. It suits general dubbing and dialogue changes; Sync Lipsync 2.0 Pro adds finer detail around teeth and facial hair.
Prompts to try with Sync Lipsync 2.0 in Claude
Copy an example into Claude, or ask in your own words.
Use Sync Lipsync 2.0 to match the supplied talking-head video to the supplied Spanish recording. Check that the presenter is already speaking in the source footage.
Use Sync Lipsync 2.0 to match this instructor video to the supplied Japanese narration. Flag any sections where the instructor’s mouth is still before proceeding.
Use Sync Lipsync 2.0 to make separate previews of this presenter video with the two supplied greeting recordings. Label each preview with the intended recipient.
Make a talking-head video with Sync Lipsync 2.0 from this headshot and this 20-second voiceover.
Create a 15-second founder intro with Sync Lipsync 2.0 using the photo and script I attach.
How to set up Sync Lipsync 2.0 in Claude
Pick the way that suits you. Each takes about two minutes.
Use the Claude connector
- Add Spiral to Claude
Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:
https://api.spiral.ai/mcp
- Keep the detected sign-in and click Add
Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.
- Click Connect
The connector page opens. Connect takes you to Spiral in your browser.
Use the Spiral skill
- Send Claude 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 Lipsync 2.0
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/v2", "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: Claude finds Sync Lipsync 2.0 on Spiral, shows the price and runs it.
Sync Lipsync 2.0 providers and prices
Spiral runs Sync Lipsync 2.0 through fal. Open a card for today's price, with every fee included.
Settings you can ask for
Sync Lipsync 2.0 works from your video URL and audio URL. Ask Claude for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Model | lipsync-2 or lipsync-2-pro | lipsync-2 | The model to use for lipsyncing. |
| Sync mode | cut_off, loop, bounce, silence, or remap | cut_off | Lipsync mode when audio and video durations are out of sync. |
Every API field of Sync Lipsync 2.0 is on its tool page: open its card above.
What can you do with Sync Lipsync 2.0 in Claude?
Make a recorded presenter speak a translated or revised audio track while retaining their speaking style. Ask your chat app to use Sync Lipsync 2 with the supplied footage and finished speech, then review the result.
Localize instructor-led lessons
Match an instructor’s talking footage to separately recorded translations for learners in other languages.
Dub creator videos
Give a talking-head video a translated speech track with mouth movements that follow the new recording.
Personalize sales greetings
Reuse a recorded presenter with separately prepared greetings for individual prospects.
Adapt customer onboarding videos
Match a presenter’s footage to new onboarding messages for different customers or audiences.
Replace a recorded line
Pair an existing talking shot with a corrected audio take, then review whether the mouth movement fits the replacement dialogue.
Add dialogue to generated humans
Match an AI-generated human’s visible speaking motion to a finished voice recording.
Localize animated dialogue
Use an existing animated talking shot with a human-like face and a translated dialogue recording.
More on Sync Lipsync 2.0 and Claude
Overview
Sync Lipsync 2.0 in other agents
Questions about Sync Lipsync 2.0 in Claude
Can Claude use Sync Lipsync 2.0?
Yes. Add Spiral to Claude as an MCP server, and Claude can find and run Sync Lipsync 2.0 like any built-in tool.
How much does Sync Lipsync 2.0 cost in Claude?
Up to $3.90 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 Claude plan is separate.
Do I need a fal account to use Sync Lipsync 2.0 in Claude?
No. Spiral runs Sync Lipsync 2.0 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 Lipsync 2.0 in Claude?
About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.
Does Claude wait while Sync Lipsync 2.0 runs?
Sync Lipsync 2.0 runs in the background. Claude starts the run, checks on it and gives you the video when it's ready.
What does Sync Lipsync 2 change in a video?
It changes the speaker’s lip movements to match a replacement audio track. Use it to dub talking footage or change dialogue while retaining the speaker’s visual speaking style.
Can Sync Lipsync 2 work with different languages?
Yes. Supply the translated speech as audio, and it can match the speaker’s lips to that recording in any language.
Can I start with a still photo?
Use video that already shows natural speaking motion. Still frames and inactive mouths do not provide the motion Sync Lipsync 2 needs for reliable results.
Is the finished video only 512×512?
The 512×512 limit describes the generated face region. The face is placed back into the original frame, and the output retains the source video’s dimensions and orientation.
Does Sync Lipsync 2 work on animated characters?
It can work on animated characters with human-like faces. Animals and non-humanoid characters are unsupported, so start with a short test before processing a longer scene.
Start using Sync Lipsync 2.0 in Claude
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude:
set up https://spiral.ai/SKILL.md


