Communitygithub.com

NeverSight/learn-skills.dev

在程序化视频中添加音频时使用此技能——使用ElevenLabs TTS生成旁白、获取免版税背景音乐、用FFmpeg创建音效、实现音频闪避或在Remotion中混合多个音频层。

learn-skills.dev 是什么?

此技能专注于为程序化视频提供全面的音频设计解决方案。它涵盖从使用ElevenLabs、OpenAI TTS和Edge TTS等提供商生成旁白,到用FFmpeg创建合成音效以及获取免版税背景音乐的全流程。该技能强调了分层音频架构(旁白、音效和背景音乐)以及音频闪避(在旁白播放期间自动降低背景音乐音量)和基于帧的音频同步等关键技术。它提供了在Remotion中实现这些模式的可直接使用的TypeScript代码示例,包括用于生成旁白、配置语音设置、实施闪避逻辑和混合多个音频层的实用函数。通过遵循本技能中概述的最佳实践和反模式,开发者可以避免常见的陷阱,例如旁白在背景下难以听清、音量剪辑以及音频不同步。

兼容平台✓Claude Code✓Codex CLI~Cursor✓Gemini CLI
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/absolutelyskilled/absolutelyskilled/video-audio-design

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

文档

当此技能被激活时,始终以 :speaker: 表情符号开始你的第一个回复。

视频音频设计

视频音频设计是将旁白、音效和背景音乐分层融入程序化视频合成的实践。出色的音频能将幻灯片式的视频转变为精美的制作——旁白引导观众,音乐设定情感基调,音效则强调关键时刻。本技能涵盖使用ElevenLabs及其他TTS提供商生成语音、用FFmpeg创建合成音效、获取免版税背景音乐、实现音频闪避以确保语音清晰,以及在Remotion合成中以帧级精度混合所有音频层。


何时使用此技能

在以下情况下触发此技能:

  • 用户想要为程序化视频添加旁白或画外音
  • 需要使用ElevenLabs、OpenAI TTS或Edge TTS生成语音
  • 询问关于语音选择、语音设置或语音克隆
  • 想要添加背景音乐或需要免版税音乐来源
  • 询问如何程序化创建音效
  • 想要实现音频闪避(在语音期间降低音乐音量)
  • 需要在Remotion中混合多个音频层
  • 询问关于音频时序、音量级别或基于帧的音频同步

在以下情况下不要触发此技能:

  • 视频脚本编写或分镜——使用 video-scriptwriting 技能
  • Remotion组件架构或渲染——使用 remotion-video 技能
  • 在DAW(Ableton、Logic、Pro Tools)中的专业音频制作
  • 音乐作曲或MIDI编程

关键原则

  1. 分层音频架构 - 每个视频都有三个音频层: 旁白在最上层(最大声),音效在中间(强调音量),背景音乐在最底层(最安静)。

  2. 旁白驱动时序 - 先生成旁白,测量其时长,然后设置场景时间以匹配。切勿将旁白强行放入任意场景长度中。

  3. 在语音期间闪避音乐 - 当旁白播放时,背景音乐必须降低50-60%。使用平滑的渐变(10-15帧)以避免突兀的跳变。

  4. 音效应作为强调而非干扰 - 保持音效简短(0.5秒以内),音量柔和,并与屏幕上的动作相关。

  5. 在上下文中测试音频 - 务必预览包含所有层的完整混音。留意听不清的语音、音量峰值或寂静无声。


核心概念

3层音频架构

层作用基础音量旁白播放期间
旁白传达信息,驱动节奏0.8-1.0不适用(顶层)
音效强调过渡和动作0.3-0.50.3-0.5(不变)
背景音乐设定情感基调,填充静音0.3-0.50.15-0.25(闪避)

ElevenLabs API 模型

ElevenLabs通过REST API提供神经TTS。核心流程:

  1. 选择一个语音(预制或克隆的) - 每个语音都有一个 voice_id
  2. 将文本 + 语音设置发送到 /v1/text-to-speech/{voice_id}
  3. 接收原始音频字节(默认格式为mp3)
  4. 写入文件并测量时长以用于场景时序

语音设置:

设置范围低高推荐
stability0-1更具表现力,多变更一致,单调0.4-0.6
similarity_boost0-1更具创造性更接近原声0.6-0.8
style0-1中性表达夸张风格0.3-0.6

音频闪避概念

音频闪避在旁白开始时降低背景音乐音量,并在旁白结束时恢复。在Remotion中,使用 interpolate():

音乐音量:  0.4 ---\              /--- 0.4
                   \            /
           0.15     \__________/
                旁白开始 → 结束

渐变应占用10-15帧(在30fps下约0.3-0.5秒)。

Remotion中的基于帧的音频同步

  • useCurrentFrame() 返回当前帧编号
  • interpolate() 将帧范围映射到值范围(例如音量)
  • <Sequence from={frame}> 将音频放置在特定帧处
  • <Audio volume={fn}> 接受一个静态数字或一个逐帧函数

将秒转换为帧:frames = seconds * fps。


常见任务

1. 设置ElevenLabs API密钥并生成旁白

import fs from 'fs';

const ELEVENLABS_API_URL = 'https://api.elevenlabs.io/v1';

async function generateNarration(
  text: string,
  voiceId: string,
  outputPath: string
): Promise<void> {
  const response = await fetch(
    `${ELEVENLABS_API_URL}/text-to-speech/${voiceId}`,
    {
      method: 'POST',
      headers: {
        'Content-Type': 'application/json',
        'xi-api-key': process.env.ELEVEN_LABS_API_KEY!,
      },
      body: JSON.stringify({
        text,
        model_id: 'eleven_multilingual_v2',
        voice_settings: {
          stability: 0.5,
          similarity_boost: 0.75,
          style: 0.5,
          use_speaker_boost: true,
        },
      }),
    }
  );

  if (!response.ok) {
    const error = await response.text();
    throw new Error(`ElevenLabs API error ${response.status}: ${error}`);
  }

  const buffer = Buffer.from(await response.arrayBuffer());
  fs.writeFileSync(outputPath, buffer);
}

2. 选择并配置语音设置

语音选择问题:性别、年龄范围、口音、精力水平、温暖度。

interface VoiceSettings {
  stability: number;
  similarity_boost: number;
  style: number;
  use_speaker_boost: boolean;
}

const presets: Record<string, VoiceSettings> = {
  explainer: { stability: 0.6, similarity_boost: 0.75, style: 0.4, use_speaker_boost: true },
  promo: { stability: 0.3, similarity_boost: 0.7, style: 0.7, use_speaker_boost: true },
  tutorial: { stability: 0.7, similarity_boost: 0.8, style: 0.2, use_speaker_boost: false },
};

3. 根据脚本为每个场景生成旁白

import { execSync } from 'child_process';
import path from 'path';

interface Scene { id: string; narrationText: string; }
interface SceneWithAudio extends Scene {
  audioPath: string;
  durationMs: number;
  durationFrames: number;
}

function getAudioDurationMs(filePath: string): number {
  const output = execSync(
    `ffprobe -v error -show_entries format=duration -of csv=p=0 "${filePath}"`
  ).toString().trim();
  return Math.round(parseFloat(output) * 1000);
}

async function generateSceneNarrations(
  scenes: Scene[], voiceId: string, outputDir: string, fps: number
): Promise<SceneWithAudio[]> {
  const results: SceneWithAudio[] = [];
  for (const scene of scenes) {
    const audioPath = path.join(outputDir, `${scene.id}.mp3`);
    await generateNarration(scene.narrationText, voiceId, audioPath);
    const durationMs = getAudioDurationMs(audioPath);
    results.push({
      ...scene, audioPath, durationMs,
      durationFrames: Math.ceil((durationMs / 1000) * fps),
    });
  }
  return results;
}

4. 获取背景音乐

免版税音乐来源:

5. 使用FFmpeg生成音效

# 点击声 - 短正弦脉冲
ffmpeg -f lavfi -i "sine=frequency=800:duration=0.05" \
  -af "afade=t=out:st=0.02:d=0.03" click.wav

# 键盘打字 - 滤波后的噪声脉冲
ffmpeg -f lavfi -i "anoisesrc=d=0.08:c=white:a=0.3" \
  -af "highpass=f=2000,lowpass=f=8000,afade=t=out:st=0.04:d=0.04" type.wav

# 呼啸声 - 频率扫描
ffmpeg -f lavfi -i "sine=frequency=200:duration=0.4" \
  -af "vibrato=f=8:d=0.5,afade=t=in:d=0.1,afade=t=out:st=0.2:d=0.2,lowpass=f=1000" \
  whoosh.wav

# 叮当声 - 铃声合成
ffmpeg -f lavfi -i "sine=frequency=1200:duration=0.6" \
  -af "afade=t=out:st=0.1:d=0.5,aecho=0.8:0.88:40:0.4" ding.wav

# 爆破声 - 脉冲
ffmpeg -f lavfi -i "sine=frequency=400:duration=0.08" \
  -af "afade=t=out:st=0.02:d=0.06,lowpass=f=600" pop.wav

# 过渡嗖声
ffmpeg -f lavfi -i "sine=frequency=300:duration=0.3" \
  -af "vibrato=f=12:d=0.8,afade=t=in:d=0.05,afade=t=out:st=0.15:d=0.15,bandpass=f=500:w=400" \
  swoosh.wav

6. 在Remotion中实现音频闪避

import React from 'react';
import { Audio, useCurrentFrame, interpolate, Sequence } from 'remotion';

const AudioMixer: React.FC<{
  narrationSrc: string;
  musicSrc: string;
  narrationStart: number;
  narrationDuration: number;
}> = ({ narrationSrc, musicSrc, narrationStart, narrationDuration }) => {
  const frame = useCurrentFrame();

  const duckRampFrames = 10;
  const musicVolume = interpolate(
    frame,
    [
      narrationStart - duckRampFrames,
      narrationStart,
      narrationStart + narrationDuration,
      narrationStart + narrationDuration + duckRampFrames,
    ],
    [0.4, 0.15, 0.15, 0.4],
    { extrapolateLeft: 'clamp', extrapolateRight: 'clamp' }
  );

  return (
    <>
      <Audio src={musicSrc} volume={musicVolume} />
      <Sequence from={narrationStart} durationInFrames={narrationDuration}>
        <Audio src={narrationSrc} volume={0.9} />
      </Sequence>
    </>
  );
};

export default AudioMixer;

7. 在Remotion合成中混合3个音频层

import React from 'react';
import { Audio, Sequence, useCurrentFrame, interpolate } from 'remotion';

interface NarrationSegment { src: string; startFrame: number; durationFrames: number; }
interface SfxEvent { src: string; frame: number; }

const FullAudioMix: React.FC<{
  narrations: NarrationSegment[];
  sfxEvents: SfxEvent[];
  musicSrc: string;
}> = ({ narrations, sfxEvents, musicSrc }) => {
  const frame = useCurrentFrame();
  const duckRamp = 10;

  let musicVolume = 0.4;
  for (const seg of narrations) {
    const duck = interpolate(
      frame,
      [seg.startFrame - duckRamp, seg.startFrame,
       seg.startFrame + seg.durationFrames, seg.startFrame + seg.durationFrames + duckRamp],
      [1, 0.375, 0.375, 1],
      { extrapolateLeft: 'clamp', extrapolateRight: 'clamp' }
    );
    musicVolume = musicVolume * duck;
  }

  return (
    <>
      <Audio src={musicSrc} volume={musicVolume} loop />
      {sfxEvents.map((sfx, i) => (
        <Sequence key={i} from={sfx.frame} durationInFrames={30}>
          <Audio src={sfx.src} volume={0.4} />
        </Sequence>
      ))}
      {narrations.map((seg, i) => (
        <Sequence key={i} from={seg.startFrame} durationInFrames={seg.durationFrames}>
          <Audio src={seg.src} volume={0.9} />
        </Sequence>
      ))}
    </>
  );
};

export default FullAudioMix;

8. 使用替代TTS提供商

OpenAI TTS - 质量好,API简单,六种内置语音:

import OpenAI from 'openai';
import fs from 'fs';

const openai = new OpenAI();

async function generateWithOpenAI(
  text: string,
  outputPath: string,
  voice: 'alloy' | 'echo' | 'fable' | 'onyx' | 'nova' | 'shimmer' = 'alloy'
): Promise<void> {
  const mp3 = await openai.audio.speech.create({
    model: 'tts-1-hd',
    voice,
    input: text,
  });
  const buffer = Buffer.from(await mp3.arrayBuffer());
  fs.writeFileSync(outputPath, buffer);
}

Edge TTS - 免费,多种语音,使用Microsoft Edge的TTS服务:

pip install edge-tts
edge-tts --voice en-US-AriaNeural --text "Hello world" --write-media output.mp3
edge-tts --list-voices

反模式 / 常见错误

错误为什么错误应该怎么做
旁白播放期间音乐音量不变语音变得难以听清实现音频闪避 - 在语音期间将音乐音量降低50-60%
硬编码ElevenLabs API密钥密钥会泄露到版本控制中使用环境变量:process.env.ELEVEN_LABS_API_KEY
使用TTS而不测量时长场景时间错误,旁白被切断生成后使用ffprobe测量音频时长
音效比旁白更响分散观众对内容的注意力音效音量为0.3-0.5,旁白音量为0.8-1.0
音乐开始/结束没有淡入淡出突然的开始/停止听起来像bug在开始处添加0.5-1秒淡入,在结束处添加淡出
使用低质量TTS模型机械音质降低整体质量使用eleven_multilingual_v2或tts-1-hd
忽略音频文件格式某些格式会添加静音填充旁白使用MP3,音效使用WAV

注意事项与陷阱

  1. ElevenLabs速率限制和字符配额 - 免费套餐有月度字符限制。积极缓存生成的音频,仅在文本更改时重新生成。使用文本的哈希值作为缓存键。

  2. MP3编码器填充会添加静音 - MP3文件开头通常有20-50ms的静音。使用 ffmpeg -af silenceremove=1:0:-50dB 修剪,或者在帧时间中考虑此偏移。

  3. Remotion Audio音量是组件级别的,而非全局的 - 两个音量为1.0的 <Audio> 组件可能会削波。保持同时播放层的总音量低于1.0。

  4. FFmpeg音效在不同系统上听起来不同 - 始终指定 -ar 44100 -sample_fmt s16 以确保跨机器的输出一致。

  5. 跨场景的语音一致性 - 对于相同的设置和不同的文本,ElevenLabs可能产生不同的语调。对于多场景旁白,使用 stability >= 0.5。


参考

有关特定音频子领域的详细模式,请阅读 references/ 文件夹中的相关文件:

  • references/elevenlabs-api.md - 高级ElevenLabs API模式,包括语音克隆、流式TTS、WebSocket API、发音词典和配额管理
  • references/audio-mixing-patterns.md - 高级混音模式,包括多段闪避、场景间的交叉淡入淡出、音量自动化曲线和最终混音的母带处理
  • references/sfx-generation.md - 使用FFmpeg的综合音效生成,包括复杂合成、多层生成器以及构建可复用的音效库

仅当当前任务需要时才加载参考文件 - 它们很长且会消耗上下文。


伴侣检查

首次激活时...

… [为翻译截断]

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

NeverSight/learn-skills.dev

Use when generating or modifying Remotion video code, creating demo videos, or working with the demo-video/ directory

NeverSight/learn-skills.dev

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric, PixVerse. Audio: Inworld TTS-2 (100+ languages, emotion steering for characters), ElevenLabs, Kokoro. Capabilities: audio-driven avatars, text-to-avatar, lipsync videos, talking head generation, virtual presenters, UGC content. Use for: AI presenters, explainer videos, virtual influencers, dubbing, marketing videos, UGC ads, gaming avatars, NPC dialogue. Triggers: ai avatar, talking head, lipsync, avatar video, virtual presenter, ai spokesperson, audio driven video, heygen alternative, synthesia alternative, talking avatar, lip sync, video avatar, ai presenter, digital human, ugc, ugc video, ugc ad, avatar ugc

NeverSight/learn-skills.dev

Create AI marketing videos for ads, promos, product launches, and brand content. Models: Veo, Seedance, Wan, FLUX for visuals, Kokoro for voiceover. Types: product demos, testimonials, explainers, social ads, brand videos. Use for: Facebook ads, YouTube ads, product launches, brand awareness. Triggers: marketing video, ad video, promo video, commercial, brand video, product video, explainer video, ad creative, video ad, facebook ad video, youtube ad, instagram ad, tiktok ad, promotional video, launch video

NeverSight/learn-skills.dev

Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse

NeverSight/learn-skills.dev

ElevenLabs automatic dubbing - translate and dub audio/video into 29 languages while preserving speaker voice via inference.sh CLI. Capabilities: auto speaker detection, voice-preserving translation, video dubbing, audio localization. Use for: content localization, video translation, multilingual content, international distribution. Triggers: dubbing, dub video, translate audio, video translation, audio translation, localize content, elevenlabs dubbing, eleven labs dub, multilingual dub, voice translation, auto dub, language dub, content localization

NeverSight/learn-skills.dev

Explainer video production guide: scripting, voiceover, visuals, and assembly. Covers script formulas, pacing rules, scene planning, and multi-tool pipelines. Use for: product demos, how-it-works videos, onboarding videos, social explainers. Triggers: explainer video, how to make explainer, product video, demo video, video production, video script, animated explainer, product demo video, tutorial video, onboarding video, walkthrough video, video pipeline

NeverSight/learn-skills.dev

Still-to-video conversion guide: model selection, motion prompting, and camera movement. Covers Wan 2.5 i2v, Seedance, Fabric, Grok Video with when to use each. Use for: animating images, creating video from stills, adding motion, product animations. Triggers: image to video, i2v, animate image, still to video, add motion to image, image animation, photo to video, animate still, wan i2v, image2video, bring image to life, animate photo, motion from image

NeverSight/learn-skills.dev

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

NeverSight/learn-skills.dev

Generate videos with Pruna P-Video and WAN models via inference.sh CLI. Models: P-Video, WAN-T2V, WAN-I2V. Capabilities: text-to-video, image-to-video, audio support, 720p/1080p, fast inference. Pruna optimizes models for speed without quality loss. Triggers: pruna video, p-video, pruna ai video, fast video generation, optimized video, wan t2v, wan i2v, economic video generation, cheap video generation, pruna text to video, pruna image to video

NeverSight/learn-skills.dev

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

NeverSight/learn-skills.dev

Video ad creation with exact platform-specific specs for TikTok, Instagram, YouTube, Facebook, LinkedIn. Covers dimensions, duration limits, AIDA framework, and caption requirements. Use for: video ads, social media ads, paid media creative, video marketing, ad production. Triggers: video ad, social media ad, tiktok ad, instagram ad, youtube ad, facebook ad, linkedin ad, video creative, ad specs, paid media, video marketing, ad production, reels ad, stories ad, pre roll, bumper ad

NeverSight/learn-skills.dev

Best practices and techniques for writing effective AI video generation prompts. Covers: Veo, Seedance, Wan, Grok, Kling, Runway, Pika, Sora prompting strategies. Learn: shot types, camera movements, lighting, pacing, style keywords, negative prompts. Use for: improving video quality, getting consistent results, professional video prompts. Triggers: video prompt, how to prompt video, veo prompts, video generation tips, better ai video, video prompt engineering, video prompt guide, video prompt template, ai video tips, video prompt best practices, video prompt examples, cinematography prompts

NeverSight/learn-skills.dev

YouTube thumbnail design with specific dimensions, contrast rules, and mobile preview optimization. Covers safe zones, text placement, face expression psychology, and A/B testing. Use for: YouTube thumbnails, video cover images, click-through optimization. Triggers: youtube thumbnail, thumbnail design, video thumbnail, click through rate, ctr optimization, youtube cover, video cover image, thumbnail maker, thumbnail tips, youtube design, video preview image

NeverSight/learn-skills.dev

Landing page conversion optimization with layout rules, hero section design, and CTA psychology. Covers above-the-fold formula, social proof placement, mobile design, and F-pattern reading. Use for: startup landing pages, product pages, SaaS marketing, conversion optimization. Triggers: landing page, hero section, above the fold, conversion optimization, landing page design, cta button, hero image, landing page layout, saas landing page, product page design, conversion rate, landing page best practices

NeverSight/learn-skills.dev

Configure and use the hosted YouTube Data MCP end-to-end with minimal user input. Use when users want the agent to verify Node.js and `npx`, configure MCP server config (Windows/macOS, Cursor/Codex/OpenClaw/OpenCode), request API key at setup time, run post-install capability discovery (`tools/list` and `get_patch_notes`), and then strongly recommend helper skill and Python setup for full local document and spreadsheet workflows.

NeverSight/learn-skills.dev

Creates 120fps GPU-accelerated animations with Motion.dev (Framer Motion successor) for React, Next.js, Svelte, and Astro projects. Use when user requests animation, motion, scroll effects, parallax, hero animations, gestures, drag interactions, spring physics, whileHover effects, whileInView animations, animated UI, micro-interactions, page transitions, or layout animations. Generates production TypeScript/JSX code with accessibility (prefers-reduced-motion) and performance validation (≥60fps). Supports entrance animations, gesture interactions (hover/tap/drag), scroll-based reveals, and layout transitions using spring physics and natural timing. Do NOT use for CSS-only transitions (use native CSS), static sites without JavaScript, Vue animations (use motion-v variant instead), or SVG/Canvas complex animations (GSAP better suited).

NeverSight/learn-skills.dev

Static artifact craft skill for self-contained HTML/CSS/JS documents: docs, sheets, dashboards, explainers, slides, tools, and landing pages. Use when the user asks for a durable, openable, shareable web deliverable they'll keep or hand off — a report, a dashboard, a slide deck, a data table, a page. Local folder first, temporary public link via tunnel (localhost.run), optional durable publish to Surge, GitHub Pages, or Cloudflare. Not for quick look renders, inline snippets, or throwaway scratch. Not for SPA frameworks, backend APIs, database apps, or production product UI.

NeverSight/learn-skills.dev

FFmpeg commands for video/audio conversion, trimming, compression, and processing. Use when user mentions "ffmpeg", "convert video", "compress video", "extract audio", "trim video", "gif from video", "video codec", "transcode", "screen recording", "merge videos", "video to mp4", "reduce file size", or any media processing task.

NeverSight/learn-skills.dev

Vim keybindings, motions, text objects, and operators for efficient text editing. Use when user asks about "vim commands", "vim motions", "text objects", "vim keybindings", "vim cheat sheet", "learn vim", "vim in VS Code", or any Vim editing tasks.

NeverSight/learn-skills.dev

Grok Build ONLY. Turn a 2D character still into smooth animation sprites via image_gen/image_edit base → image_to_video (6s/10s run-in-place) → ffmpeg frames → magenta chroma-key → dense sampled sprites (strip/grid/GIF). Use when the user wants video-to-sprite, motion capture from generated video, smoother run/walk cycles from dense frames, or runs /video2dsprite. Do NOT use on Codex/Claude — only Grok Build has image_to_video. Prefer generate2dsprite for crisp pixel sheets without video.

相关技能