tools/video/remotion-render/SKILL.md
Render videos from React/Remotion component code via inference.sh. Pass TSX code, get MP4. Supports all Remotion APIs: useCurrentFrame, useVideoConfig, spring, interpolate, AbsoluteFill, Sequence. Configurable resolution, FPS, duration, codec. Use for: programmatic video generation, animated graphics, motion design, data-driven videos, React animations to video. Triggers: remotion, render video from code, tsx to video, react video, programmatic video, remotion render, code to video, animated video, motion graphics code, react animation video
npx skillsauth add inference-sh-5/skills remotion-renderInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Install the belt CLI skill:
npx skills add belt-sh/cli
Render videos from React/Remotion component code via inference.sh CLI.

Requires inference.sh CLI (
belt). Install instructions
belt login
# Render a simple animation
belt app run infsh/remotion-render --input '{
"code": "import { useCurrentFrame, AbsoluteFill } from \"remotion\"; export default function Main() { const frame = useCurrentFrame(); return <AbsoluteFill style={{backgroundColor: \"#000\", display: \"flex\", justifyContent: \"center\", alignItems: \"center\"}}><h1 style={{color: \"white\", fontSize: 100, opacity: frame / 30}}>Hello World</h1></AbsoluteFill>; }",
"duration_seconds": 3,
"fps": 30,
"width": 1920,
"height": 1080
}'
| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| code | string | Yes | React component TSX code. Must export default a component. |
| composition_id | string | No | Composition ID to render |
| props | object | No | Props passed to the component |
| width | number | No | Video width in pixels |
| height | number | No | Video height in pixels |
| fps | number | No | Frames per second |
| duration_seconds | number | No | Video duration in seconds |
| codec | string | No | Output codec |
Your TSX code can import from remotion and react:
// Remotion APIs
import {
useCurrentFrame,
useVideoConfig,
spring,
interpolate,
AbsoluteFill,
Sequence,
Audio,
Video,
Img
} from "remotion";
// React
import React, { useState, useEffect } from "react";
belt app run infsh/remotion-render --input '{
"code": "import { useCurrentFrame, AbsoluteFill, interpolate } from \"remotion\"; export default function Main() { const frame = useCurrentFrame(); const opacity = interpolate(frame, [0, 30], [0, 1]); return <AbsoluteFill style={{backgroundColor: \"#1a1a2e\", display: \"flex\", justifyContent: \"center\", alignItems: \"center\"}}><h1 style={{color: \"#eee\", fontSize: 80, opacity}}>Welcome</h1></AbsoluteFill>; }",
"duration_seconds": 2,
"fps": 30,
"width": 1920,
"height": 1080
}'
belt app run infsh/remotion-render --input '{
"code": "import { useCurrentFrame, useVideoConfig, AbsoluteFill } from \"remotion\"; export default function Main() { const frame = useCurrentFrame(); const { fps, durationInFrames } = useVideoConfig(); const progress = Math.floor((frame / durationInFrames) * 100); return <AbsoluteFill style={{backgroundColor: \"#000\", display: \"flex\", justifyContent: \"center\", alignItems: \"center\", flexDirection: \"column\"}}><h1 style={{color: \"#fff\", fontSize: 200}}>{progress}%</h1><p style={{color: \"#666\", fontSize: 30}}>Loading...</p></AbsoluteFill>; }",
"duration_seconds": 5,
"fps": 60,
"width": 1080,
"height": 1080
}'
belt app run infsh/remotion-render --input '{
"code": "import { useCurrentFrame, useVideoConfig, spring, AbsoluteFill } from \"remotion\"; export default function Main() { const frame = useCurrentFrame(); const { fps } = useVideoConfig(); const scale = spring({ frame, fps, config: { damping: 10, stiffness: 100 } }); return <AbsoluteFill style={{backgroundColor: \"#6366f1\", display: \"flex\", justifyContent: \"center\", alignItems: \"center\"}}><div style={{width: 200, height: 200, backgroundColor: \"white\", borderRadius: 20, transform: `scale(${scale})`}} /></AbsoluteFill>; }",
"duration_seconds": 2,
"fps": 60,
"width": 1080,
"height": 1080
}'
belt app run infsh/remotion-render --input '{
"code": "import { AbsoluteFill } from \"remotion\"; export default function Main({ title, subtitle }) { return <AbsoluteFill style={{backgroundColor: \"#000\", display: \"flex\", justifyContent: \"center\", alignItems: \"center\", flexDirection: \"column\"}}><h1 style={{color: \"#fff\", fontSize: 80}}>{title}</h1><p style={{color: \"#888\", fontSize: 40}}>{subtitle}</p></AbsoluteFill>; }",
"props": {"title": "My Video", "subtitle": "Created with Remotion"},
"duration_seconds": 3,
"fps": 30,
"width": 1920,
"height": 1080
}'
belt app run infsh/remotion-render --input '{
"code": "import { useCurrentFrame, AbsoluteFill, Sequence, interpolate } from \"remotion\"; function FadeIn({ children }) { const frame = useCurrentFrame(); const opacity = interpolate(frame, [0, 20], [0, 1]); return <div style={{ opacity }}>{children}</div>; } export default function Main() { return <AbsoluteFill style={{backgroundColor: \"#000\", display: \"flex\", justifyContent: \"center\", alignItems: \"center\", flexDirection: \"column\", gap: 20}}><Sequence from={0}><FadeIn><h1 style={{color: \"#fff\", fontSize: 60}}>First</h1></FadeIn></Sequence><Sequence from={30}><FadeIn><h1 style={{color: \"#fff\", fontSize: 60}}>Second</h1></FadeIn></Sequence><Sequence from={60}><FadeIn><h1 style={{color: \"#fff\", fontSize: 60}}>Third</h1></FadeIn></Sequence></AbsoluteFill>; }",
"duration_seconds": 4,
"fps": 30,
"width": 1920,
"height": 1080
}'
from inferencesh import inference
client = inference()
result = client.run({
"app": "infsh/remotion-render",
"input": {
"code": """
import { useCurrentFrame, AbsoluteFill, interpolate } from "remotion";
export default function Main() {
const frame = useCurrentFrame();
const opacity = interpolate(frame, [0, 30], [0, 1]);
return (
<AbsoluteFill style={{
backgroundColor: "#1a1a2e",
display: "flex",
justifyContent: "center",
alignItems: "center"
}}>
<h1 style={{ color: "#eee", fontSize: 80, opacity }}>
Hello from Python
</h1>
</AbsoluteFill>
);
}
""",
"duration_seconds": 3,
"fps": 30,
"width": 1920,
"height": 1080
}
})
print(result["output"]["video"])
for update in client.run({
"app": "infsh/remotion-render",
"input": {
"code": "...",
"duration_seconds": 10
}
}, stream=True):
if update.get("progress"):
print(f"Rendering: {update['progress']}%")
if update.get("output"):
print(f"Video: {update['output']['video']}")
# Remotion best practices (component patterns)
npx skills add remotion-dev/skills@remotion-best-practices
# AI video generation (for AI-generated clips)
npx skills add inference-sh/skills@ai-video-generation
# Image generation (for video assets)
npx skills add inference-sh/skills@ai-image-generation
# Python SDK reference
npx skills add inference-sh/skills@python-sdk
# Full platform skill
npx skills add inference-sh/skills@infsh-cli
data-ai
Generate multi-person talking head podcast videos from scratch using AI — character creation, TTS, avatar animation, and video stitching. Use when the user wants to create a podcast, talking head video, or multi-speaker conversation video.
tools
Generate videos with ByteDance Seedance 2.0 via inference.sh CLI. Unified model for text-to-video, image-to-video, and reference-to-video with synchronized audio, up to 1080p, 4-15s duration. Pro and Fast variants. Studio variants with private asset library for portrait consistency. Use for: social media videos, music videos, product demos, animated content, AI video with sound. Triggers: seedance, seedance 2, bytedance video, seedance t2v, seedance i2v, seedance r2v, video with audio, seedance 2.0, bytedance seedance, seedance studio
tools
Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative
tools
Generate and edit videos with Alibaba HappyHorse 1.0 models via inference.sh CLI. Models: HappyHorse T2V, I2V, R2V, Video Edit. Capabilities: text-to-video, image-to-video, reference-to-video, video editing with natural language, character preservation, 720P/1080P, up to 15 seconds. Use for: physically realistic video, video editing, character-consistent content, product demos, social media. Triggers: happyhorse, happy horse, alibaba video, happyhorse 1.0, dashscope video, alibaba happyhorse, video editing ai, ai video editor