- Home
- Skills
- Agents & Orchestration
- create voiced ad
More screenshots
Works with the AI Agents you already use
create voiced ad
Generate animated SVG video ads with synchronized AI voiceovers, character gestures, and mobile app captures.
Free
create voiced ad
Example session with this skill installed
Create a 45-second TikTok ad for my budgeting app. The character should look like a young professional, use the 'Antoni' voice, and show the expense tracking screen.
- Read your context and instructions
- Compiled the create voiced ad
I have scripted and prepared the video assets for your budgeting app advertisement. The script consists of 6 scenes focused on the pain point of hidden expenses, ending with a "link in bio" call to action.
Ad Production Summary
| Asset | Specification | Status |
|---|---|---|
| Script | 52 seconds, 7 scenes | Verified |
| Voice | Antoni (ElevenLabs) | Generated |
| Formats | 1080x1920 (Vertical), 1920x1080 (Horizontal) | Ready |
| Character | Young Professional SVG (IK rigged) | Configured |
| Audio | Lo-fi beats with ducking (-15 LUFS) | Mixed |
// src/video/acting.ts excerpt
export const acting = {
scene1: [
{ word: "hidden", action: "frown", gesture: "point" },
{ word: "fees", action: "shake_head", cue: "POPS" },
],
scene3: [
{ word: "track", action: "smile", gesture: "phone", zoom: "tight" },
{ word: "instantly", action: "nod", cue: "DING" }
]
};
Next steps
- Review the generated
grid.pngstoryboard to verify character positioning and captions. - Run
pnpm run video:render:verticalto produce the final TikTok MP4. - Check
references/journal.mdfor the updated logs of this production run.
Connects securely to your tools. The creator never sees your data.
About this skill
Stop wasting budget on static, boring presentation-style ads that users scroll past. This skill builds high-energy, animated video ads using Remotion and ElevenLabs, featuring a synchronized SVG character that actually interacts with your application interface.
What it does
- Animated Characters creates an articulated SVG character with inverse kinematics for natural gestures and lip-sync.
- Automated Voiceover generates high-quality TTS using ElevenLabs with precise word-level timestamps for animation syncing.
- App Interaction renders real mobile viewport captures within the character's hand, including zooms, scrolls, and taps.
- Dynamic Compositions produces both 9:16 vertical (Reels/TikTok) and 16:9 horizontal (YouTube) formats in a single pass.
- Audio Engineering handles background music ducking, sound effect triggers, and LUFS normalization for professional sound.
How it works
- Scripting defines a 5-7 scene sequence focused on a problem-solution hook with verified data points.
- Audio Generation fetches ElevenLabs voices and music, generating a timing JSON for character mouth movements.
- Visual Acting maps specific character gestures and camera "punches" to individual words in the script.
- Rendering validates alignment via Vitest, generates a visual storyboard for approval, and exports final MP4 files.
Frameworks & tools
Built on Remotion, TypeScript, and ElevenLabs API. It uses FFmpeg for audio processing, Vitest for subtitle alignment checks, and tsx for script execution.
Why this beats prompting it yourself
Manual prompting lacks the frame-perfect coordination between audio timestamps and SVG coordinate transforms. This skill manages the complex math of inverse kinematics and audio ducking that generic agents fail to synchronize correctly.
Use cases
- Launching a mobile app with a character showing specific features in hand.
- Creating localized TikTok ads with accurate French/English lip-sync and captions.
- Generating high-retention YouTube shorts with "pop" visuals and automated sound effects.
Known limitations
Requires an ElevenLabs API key and a local Remotion environment. Character visuals are limited to SVG geometry rather than photorealistic AI video.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Video Skills.
Requires ElevenLabs API key. Characters must be SVG-based (no photorealistic video). Limited to 9:16 and 16:9 formats. App captures require manual viewport setup at 375x812.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
2 uses
Times used to date
Free to use
No account required to browse
Trust & safety
Security scan
Security scan passed 20 days ago
- Free with an Agensi account
- Accounts
ElevenLabs
- Software
Git
Permissions
Allowed Hosts