Agent skill
elevenlabs-remotion
Generate professional voiceovers using ElevenLabs AI. Use when the user needs to create voiceovers for videos, audio narration, or text-to-speech content. Supports multiple voices with character presets (narrator, salesperson, expert) for natural delivery. Includes single scene regeneration for fine-tuning.
Install this agent skill to your Project
npx add-skill https://github.com/delorenj/skills/tree/main/elevenlabs-remotion
SKILL.md
ElevenLabs Voiceover Generation
Generate professional AI voiceovers for Remotion videos using ElevenLabs API.
Prerequisites
ELEVEN_API_KEYin.env.local
Quick Start
# Generate voiceover from text
node ~/.agents/skills/elevenlabs-remotion/generate.js --text "Your text here" --output public/audio/voiceover.mp3
# Generate with narrator style (more natural)
node ~/.agents/skills/elevenlabs-remotion/generate.js --text "Your text" --character narrator --output voiceover.mp3
# Generate scenes with request stitching
node ~/.agents/skills/elevenlabs-remotion/generate.js --scenes remotion/scenes.json --output-dir public/audio/project/
# Regenerate a single scene
node ~/.agents/skills/elevenlabs-remotion/generate.js --scenes scenes.json --scene scene2 --new-text "Updated text"
# List available voices and character presets
node ~/.agents/skills/elevenlabs-remotion/generate.js --list-voices
node ~/.agents/skills/elevenlabs-remotion/generate.js --list-characters
Character Presets
Use character presets for more natural voiceovers instead of literal screen text reading:
| Character | Description | Best For |
|---|---|---|
literal |
Reads text exactly as written | Screen text, quotes |
narrator |
Professional storyteller, smooth, engaging | Explainers, documentaries |
salesperson |
Enthusiastic, persuasive, energetic | Marketing, ads |
expert |
Authoritative, confident, knowledgeable | Legal content, tutorials |
conversational |
Casual, friendly, natural | Social media, casual content |
dramatic |
Intense, emotional, impactful | Hooks, problem statements |
calm |
Soothing, reassuring, gentle | Trust-building, conclusions |
# Use narrator style globally
node ~/.agents/skills/elevenlabs-remotion/generate.js --scenes scenes.json --character narrator --output-dir public/audio/
# Or set per-scene in scenes.json
{
"scenes": [
{ "id": "scene1", "text": "Problem statement", "character": "dramatic" },
{ "id": "scene2", "text": "Solution", "character": "calm" }
]
}
Scene-Based Generation with Request Stitching
Generate multiple scenes with consistent prosody using ElevenLabs request stitching:
scenes.json Format
{
"name": "product-demo",
"voice": "George",
"character": "narrator",
"scenes": [
{
"id": "scene1",
"text": "Generic text-to-speech sounds robotic. Your brand deserves better.",
"duration": 4.5,
"character": "dramatic"
},
{
"id": "scene2",
"text": "With voice cloning, you can use your own voice for unlimited content.",
"duration": 5.5
},
{
"id": "scene3",
"text": "Record a short sample. Clone it. Create professional voiceovers in minutes.",
"duration": 6,
"delay": 0.3
}
]
}
Generate All Scenes
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--scenes remotion/product-demo-scenes.json \
--output-dir public/audio/product-demo/
This creates:
product-demo-scene1.mp3throughsceneN.mp3product-demo-combined.mp3(all scenes stitched)product-demo-info.json(metadata with durations)
Single Scene Regeneration
If a scene starts too early, has wrong timing, or needs different text:
# Regenerate scene2 with new text
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--scenes remotion/scenes.json \
--scene scene2 \
--new-text "Updated scene 2 text" \
--output-dir public/audio/project/
# Regenerate scene3 with different character
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--scenes remotion/scenes.json \
--scene scene3 \
--character salesperson \
--output-dir public/audio/project/
# Just regenerate (same text, same character)
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--scenes remotion/scenes.json \
--scene scene1 \
--output-dir public/audio/project/
# Embed a thumbnail into an MP4 video
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--embed-thumbnail public/videos/my-video.mp4 \
--thumbnail public/videos/my-thumbnail.png \
--output public/videos/my-video-with-thumb.mp4
The tool automatically:
- Uses request stitching from previous scenes for consistent prosody
- Updates the info.json file with new metadata
- Updates scenes.json if
--new-textis provided
Thumbnail Embedding
Embed a thumbnail image into MP4 videos so platforms like Twitter, YouTube, and video players display your custom thumbnail instead of the first frame.
Embed Thumbnail into Video
# Basic usage - outputs to video-thumb.mp4
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--embed-thumbnail public/videos/promo.mp4 \
--thumbnail public/videos/thumbnail.png
# Custom output path
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--embed-thumbnail public/videos/promo.mp4 \
--thumbnail public/videos/thumbnail.png \
--output public/videos/promo-final.mp4
Workflow with Remotion
# 1. Render your video
npx remotion render MyVideo public/videos/my-video.mp4
# 2. Render your thumbnail (use Still composition)
npx remotion still MyVideoThumbnail public/videos/my-thumbnail.png
# 3. Embed the thumbnail
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--embed-thumbnail public/videos/my-video.mp4 \
--thumbnail public/videos/my-thumbnail.png \
--output public/videos/my-video-final.mp4
Supported Formats
- Video: MP4 (H.264/H.265)
- Thumbnail: PNG, JPG, JPEG
The embedding uses ffmpeg's -disposition:v:1 attached_pic flag to set the thumbnail as an attached picture, which most video players and platforms recognize.
Timing Validation
The skill automatically validates timing after generation using ffprobe:
What It Checks
| Check | Threshold | Description |
|---|---|---|
| Duration mismatch | >15% | Warns if actual differs from expected duration |
| Leading silence | >200ms | Audio starts late (voiceover delayed) |
| Trailing silence | >500ms | Unnecessary silence at end |
| Speaking rate | 2-4.5 wps | Optimal ~3 words/second |
Validate Existing Audio
# Validate all scenes in a project
node ~/.agents/skills/elevenlabs-remotion/generate.js --validate public/audio/product-demo/
Output example:
🔍 Validating product-demo (6 scenes)
❌ scene1: 3.00s (expected: 4.5s)
❌ Audio 1.50s shorter than expected
👍 8 words @ 3.1 words/sec
⚠️ scene2: 6.35s (expected: 5.5s)
⚠️ Leading silence: 235ms (may start late)
🐢 10 words @ 1.8 words/sec
✅ scene4: 4.36s (expected: 4s)
👍 9 words @ 2.3 words/sec
📊 Total duration: 30.80s (expected: 30.00s)
Updated info.json
After validation, the info.json includes actual measurements:
{
"scenes": [
{
"id": "scene1",
"duration": 4.5,
"actualDuration": 3.0,
"leadingSilence": 0.05,
"wordsPerSecond": 3.1
}
]
}
Use actualDuration in your Remotion composition for precise sync.
Options
| Option | Description | Default |
|---|---|---|
--text, -t |
Text to convert to speech | Required (or --file/--scenes) |
--file, -f |
Read text from file | - |
--output, -o |
Output file path | output.mp3 |
--output-dir |
Output directory for scenes | public/audio |
--voice, -v |
Voice name or ID | George |
--model, -m |
Model ID | eleven_multilingual_v2 |
--character, -c |
Character preset | literal |
--scenes |
JSON file with scenes | - |
--scene |
Regenerate single scene ID | - |
--new-text |
New text for scene regen | - |
--validate |
Validate existing audio dir | - |
--skip-validation |
Skip auto-validation | false |
--embed-thumbnail |
Video file to embed thumbnail into | - |
--thumbnail |
Thumbnail image file (PNG/JPG) | - |
--stability |
Voice stability (0-1) | varies by character |
--similarity |
Voice similarity (0-1) | varies by character |
--style |
Style exaggeration (0-1) | varies by character |
--no-combined |
Skip combined file | false |
Recommended Voices
| Voice | Style | Best For |
|---|---|---|
George |
Warm, captivating British | Narration, explainers |
Antoni |
Professional, warm | Legal content, tutorials |
Arnold |
Authoritative, deep | Corporate, serious topics |
Josh |
Friendly, conversational | Marketing, casual content |
Integration with Remotion
After generating scene voiceovers, use them in your composition:
import { Audio, Sequence, staticFile } from "remotion";
// Use individual scene audio files for precise sync
const SCENE_DURATIONS = {
scene1: 4.5, // From info.json
scene2: 5.5,
scene3: 8.0,
};
export const VideoWithVoiceover: React.FC = () => {
const { fps } = useVideoConfig();
const scene1Frames = Math.round(SCENE_DURATIONS.scene1 * fps);
const scene2Frames = Math.round(SCENE_DURATIONS.scene2 * fps);
return (
<>
<Sequence from={0} durationInFrames={scene1Frames}>
<Audio src={staticFile("audio/project/project-scene1.mp3")} />
<Scene1Visual />
</Sequence>
<Sequence from={scene1Frames} durationInFrames={scene2Frames}>
<Audio src={staticFile("audio/project/project-scene2.mp3")} />
<Scene2Visual />
</Sequence>
</>
);
};
Tips for Best Results
- Use character presets: Don't read screen text literally - use
narratororexpertfor natural flow - Punctuation matters: Use periods for pauses, commas for brief breaks
- Numbers: Write out numbers ("five hundred" not "500") for natural speech
- Abbreviations: Write full words ("twenty-four hours" not "24h")
- Scene-by-scene: Different scenes can have different characters (dramatic intro, calm CTA)
- Fine-tune: Use
--sceneto regenerate individual scenes without redoing everything - Request stitching: Keeps voice consistent across all scenes
Workflow Example
# 1. Create scenes.json with your script
# 2. Generate all scenes with narrator style
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--scenes remotion/my-video-scenes.json \
--character narrator \
--output-dir public/audio/my-video/
# 3. Preview in Remotion, notice scene2 starts too early
# 4. Regenerate just scene2 with updated text
node ~/.agents/skills/elevenlabs-remotion/generate.js \
--scenes remotion/my-video-scenes.json \
--scene scene2 \
--new-text "Slightly longer text to fill the visual timing" \
--output-dir public/audio/my-video/
# 5. Update video composition with new duration from info.json
# 6. Repeat until timing is perfect
Recommended Agent Skills
Expand your agent's capabilities with these related and highly-rated skills.
openclaw-upgrade
Upgrade OpenClaw installations to the latest version. Handles global npm installs, local development setups, release channels (stable/beta/dev), configuration preservation, and platform-specific requirements. Use when updating OpenClaw, switching release channels, or troubleshooting update issues.
vercel-composition-patterns
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture. Includes React 19 API changes.
security-monitor
Real-time security monitoring for Clawdbot. Detects intrusions, unusual API calls, credential usage patterns, and alerts on breaches.
event-driven-architecture
Kafka, RabbitMQ, SQS/SNS, event sourcing, CQRS, saga patterns, dead letter queues, and idempotency. Use when designing asynchronous systems, implementing message-driven workflows, or building event streaming pipelines.
shadcn-ui
Expert guidance for integrating and building applications with shadcn/ui components, including component discovery, installation, customization, and best practices.
just-fucking-cancel
Find and cancel unwanted subscriptions by analyzing bank transactions. Detects recurring charges, calculates annual waste, and helps you cancel with direct URLs and browser automation. Use when: 'cancel subscriptions', 'audit subscriptions', 'find recurring charges', 'what am I paying for', 'save money', 'subscription cleanup', 'stop wasting money'. Supports CSV import (Apple Card, Chase, Amex, Citi, Bank of America, Capital One, Mint, Copilot) OR Plaid API for automatic transaction pull. Outputs interactive HTML audit with one-click cancel workflow. Pairs with Plaid integration for real-time transaction access without CSV exports.
Didn't find tool you were looking for?