Skill by Mage · Lipsync

Make any portrait talk

Share a portrait and up to 15 seconds of speech, or have Seed Audio voice your line. Cherry 2 Pro makes the subject speak it in sync, with natural expressions and the framing, light, and setting of the image.

Try in Claude ↗

Requires the Mage connector ↓Prefer clicking? Open the Lipsync app →

Claude

A studio portrait of a woman with short platinum hair in a black turtleneck

Make her say my 5-second voice clip.

I saved your clip as an audio reference (free). Cherry 2 Pro at 480p, 5 s, 9:16: 773 Gems. Go ahead?

Go ahead.

Using skill · Lipsync

Attaching the portrait and the voice clip

Rendering 5 s, 9:16, 480p with Cherry 2 Pro

Waiting for the render

Here she is (Cherry 2 Pro, 480p, 5 s, 773 Gems). Check the mouth against the audio at full speed.

The platinum-haired woman saying “Hi, welcome back. Today I want to show you something new.”

Examples

A portrait and a voice

Her words match the clip; the turtleneck, light, and backdrop match the portrait.

Result · Cherry 2 Pro, 480p, 5 s

How it works

How to use the Lipsync skill

Share the subject and the speech
A front-facing portrait or a saved character, and a voice clip up to 15 seconds. No clip? Seed Audio can voice your line.
Approve the price
Cherry 2 Pro at 480p, vertical, with the shortest length that covers your audio.
Check the sync
Watch at full speed. A profile or a covered mouth is the first thing to change if it’s off.

Runs on

Cherry 2 Pro Seed Audio Lemon

Setup

Set up Mage in your agent

Connect Mage

Add the Mage connector to Claude, ChatGPT, Claude Code, Grok, or Cursor, and sign in with your Mage account.

Open MCP setup →

Add the skills

In Claude Code, Codex, Cursor, and other agents, add every Mage skill with one command, or install the Claude Code plugin.

npx skills add mage-space/skills

/plugin marketplace add mage-space/skills

/plugin install mage@mage

Ask for it

Describe the job, or run /mage-lipsync.

Use Mage to make this portrait say, in a warm, friendly voice: “Hi, welcome back. Today I want to show you something new.” Portrait: https://www.mage.space/skills/app-inputs/face.jpg

FAQ

Frequently asked questions

Is it the same as the Lipsync app?

Yes. The skill sends the Lipsync app’s own prompt with the same models and defaults, so your agent gets the app’s results from a chat, and can run it on many images in one go.

How long can the speech be?

Up to 15 seconds, the same limit as the app. Longer clips are trimmed to 15 seconds.

Can it write and voice the line for me?

Yes. Give the words and describe the voice, and the skill generates 5 or 10 seconds with Seed Audio, quotes it, and saves it as an audio reference.

Can I use a real person’s face?

Only with that person’s permission, and never to deceive, harass, or sexualize anyone. Harmful deepfakes are forbidden on Mage, and the skill states the rule with the price before it runs.

Why does it ask before rendering?

Video is priced by resolution and length, so the skill quotes the model, resolution, length, and Gems and waits for your yes. It starts at 480p, the cheapest, and offers 720p or 1080p for a final.