elevenlabs-remotion

Generate ElevenLabs text-to-speech voiceovers for Remotion video scenes.

Updated Feb 10, 2026
One-click install
npx skills add https://github.com/delorenj/00_ceiling --skill elevenlabs-remotion-delorenj
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: elevenlabs-remotion
Source: https://github.com/delorenj/00_ceiling/tree/main/elevenlabs-remotion
Command: npx skills add https://github.com/delorenj/00_ceiling --skill elevenlabs-remotion-delorenj

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

This Skill automates the creation of professional AI voiceovers for Remotion videos, streamlining audio production for video content.

Core Features & Use Cases

  • AI Voice Generation: Create high-quality text-to-speech audio using ElevenLabs.
  • Scene-Based Generation: Generate voiceovers for multiple scenes with consistent prosody and stitching.
  • Character Presets: Utilize pre-defined voice styles (narrator, salesperson, expert) for natural delivery.
  • Use Case: You need to create a marketing explainer video using Remotion and require a professional voiceover. Use this Skill to generate the audio for each scene of your video script.

Quick Start

Use the elevenlabs-remotion skill to generate a voiceover from the text 'Hello, world!' and save it to 'output.mp3'.

Frequently Asked Questions about elevenlabs-remotion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I add AI voiceovers to Remotion videos using text-to-speech?

You can generate AI voiceovers for Remotion videos by using the ElevenLabs API to convert text scripts into speech, which supports scene-based audio creation with request stitching for consistent prosody.

Can I generate voiceovers for multiple scenes and maintain consistent speech pacing?

Yes, scene-based audio creation stitches individual text-to-speech requests together, ensuring your Remotion video maintains consistent prosody and natural delivery across all scene transitions.

Does this text-to-speech generation include voice presets for different video characters?

Yes, character presets like narrator, salesperson, and expert are included to provide natural delivery, allowing you to match the AI voice style to the specific tone of your video script.

How do I validate audio timing and embed thumbnails into MP4 video files?

The skill validates audio timing using ffprobe to ensure synchronization and supports embedding thumbnails into MP4 video files, verifying that your generated voiceover matches the visual scene duration.

What is the best way to regenerate a single scene voiceover without processing the entire video script?

You can use the single scene regeneration feature to reprocess specific text-to-speech audio segments, allowing you to update individual voiceovers without regenerating the entire Remotion video script.