Communitygithub.com

NeverSight/learn-skills.dev

通过 inference.sh CLI 创建 AI 头像和说话头像视频。推荐使用 P-Video-Avatar(最快、最便宜、内置 TTS)。其他选项:OmniHuman、Fabric、PixVerse。音频:Inworld TTS-2(100+ 语言、情感控制)、ElevenLabs、Kokoro。功能:音频驱动头像、文本转头像、唇形同步视频、说话头像生成、虚拟主持人、UGC 内容。

learn-skills.dev 是什么?

这是一个帮助开发者通过 inference.sh CLI 快速创建 AI 虚拟人视频的技能。它集成了多个最先进的模型,如 P-Video-Avatar(推荐,18倍更快、6倍更便宜)、OmniHuman 1.5、Fabric 1.0 和 PixVerse,支持音频驱动、文本转头像、唇形同步等多种工作流。同时,它提供了丰富的语音合成选项,包括 Inworld TTS-2(支持 100+ 语言和情感表达)、ElevenLabs 和 Kokoro,满足不同场景下的语音需求。该技能特别适合 UGC 内容生成、营销视频、教育讲解、虚拟网红、游戏 NPC 对话等场景,并且支持批量生产、多语言本地化和端到端的视频处理流水线。

兼容平台~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/NeverSight/learn-skills.dev/tree/HEAD/data/skills-md/101-skills/skills/ai-avatar-video

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

预览

来自技能 README

AI 头像与说话头像视频

文档

安装 belt CLI 技能: npx skills add belt-sh/cli

AI 头像与说话头像视频

通过 inference.sh CLI 创建 AI 头像和说话头像视频。

AI 头像与说话头像视频

快速开始

需要 inference.sh CLI(belt)。安装说明

belt login

# 推荐:P-Video-Avatar(最快、最便宜、内置 TTS)
belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "你好,欢迎来到我们的产品演示!",
  "voice": "Zephyr (Female)"
}'

可用模型

从 P-Video-Avatar 开始——它比替代方案快 18 倍、便宜 6 倍,且内置 TTS、动态背景和 1080p 支持。

模型应用 ID最适合内置 TTS
P-Video-Avatarpruna/p-video-avatar整体最佳:速度、成本、质量、控制是(30 种声音、10 种语言)
OmniHuman 1.5bytedance/omnihuman-1-5多角色、音频驱动否
Fabric 1.0falai/fabric-1-0图像说话 + 唇形同步是
PixVerse Lipsyncfalai/pixverse-lipsync高真实度唇形同步否

成本与速度对比

模型速度(每秒钟视频)每秒成本
P-Video-Avatar~1.83s/s$0.025
OmniHuman 1.5~28s/s(慢 15 倍)$0.16(贵 6.4 倍)
Fabric 1.0~34s/s(慢 18 倍)$0.14(贵 5.6 倍)

示例

P-Video-Avatar(推荐)

通过内置 TTS 从肖像 + 文本脚本生成头像:

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "欢迎来到我们的产品介绍。今天我将向您展示三个关键功能。",
  "voice": "Puck (Male)",
  "voice_language": "Chinese (Simplified)",
  "resolution": "720p"
}'

自定义风格控制:

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "voice_script": "这是个激动人心的消息!",
  "voice": "Aoede (Female)",
  "voice_prompt": "充满热情和活力的语气",
  "video_prompt": "此人在舞台上演讲,灯光戏剧化",
  "resolution": "1080p"
}'

使用音频文件代替 TTS:

belt app run pruna/p-video-avatar --input '{
  "image": "https://portrait.jpg",
  "audio": "https://speech.mp3"
}'

完整工作流:生成肖像 + 头像

使用 Pruna P-Image 生成肖像,然后创建头像:

# 1. 生成肖像图像
belt app run pruna/p-image --input '{
  "prompt": "专业头像照,年轻女性,中性背景,看向镜头,摄影棚灯光,照片级真实感",
  "aspect_ratio": "9:16"
}'

# 2. 使用内置 TTS 创建头像视频
belt app run pruna/p-video-avatar --input '{
  "image": "<步骤 1 中的图像 URL>",
  "voice_script": "嗨!让我带您了解我们的最新功能。",
  "voice": "Zephyr (Female)"
}'

OmniHuman 1.5(多角色)

belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

支持在多人物图像中指定要驱动的角色。

Fabric 1.0(图像说话)

belt app run falai/fabric-1-0 --input '{
  "image_url": "https://face.jpg",
  "audio_url": "https://audio.mp3"
}'

PixVerse Lipsync

belt app run falai/pixverse-lipsync --input '{
  "image_url": "https://portrait.jpg",
  "audio_url": "https://speech.mp3"
}'

完整工作流:TTS + 头像(非 TTS 模型)

对于没有内置 TTS 的模型(OmniHuman、PixVerse),先生成语音:

# 1. 生成语音—Inworld TTS-2 用于富有表现力的角色声音
belt app run inworld/text-to-speech-2 --input '{
  "text": "[友好] 欢迎来到我们的产品演示![兴奋] 让我向您展示三个将改变您工作方式的功能。",
  "voice_id": "Sarah",
  "delivery_mode": "CREATIVE"
}' > speech.json

# 2. 使用生成的语音创建头像视频
belt app run bytedance/omnihuman-1-5 --input '{
  "image_url": "https://presenter-photo.jpg",
  "audio_url": "<步骤 1 中的音频 URL>"
}'

提示:对于大多数用例,带有内置 TTS 的 P-Video-Avatar 更简单—无需独立的音频生成步骤。仅在您特别需要 OmniHuman(多角色)或 PixVerse(真实唇形同步)时才使用此工作流。

完整工作流:用另一种语言配音视频

# 1. 转写原始视频
belt app run infsh/fast-whisper-large-v3 --input '{"audio_url": "https://video.mp4"}' > transcript.json

# 2. 翻译文本(手动或使用 LLM)

# 3. 以新语言生成语音
belt app run infsh/kokoro-tts --input '{"text": "<翻译后的文本>"}' > new_speech.json

# 4. 将原始视频与新音频进行唇形同步
belt app run infsh/latentsync-1-6 --input '{
  "video_url": "https://original-video.mp4",
  "audio_url": "<新音频 URL>"
}'

头像 UGC 生成

使用 P-Video-Avatar 创建 UGC 风格内容—内置 TTS,无需独立音频步骤:

# 1. 生成一张有共鸣感的 UGC 风格肖像
belt app run pruna/p-image --input '{
  "prompt": "年轻女性在舒适房间里的自拍风格照片,自然光,看着镜头,温暖微笑,真实感",
  "aspect_ratio": "9:16"
}'

# 2. 使用内置 TTS 创建 UGC 头像视频
belt app run pruna/p-video-avatar --input '{
  "image": "<步骤 1 中的图像 URL>",
  "voice_script": "好吧,我刚试了这个产品,说实话?它彻底改变了游戏规则。我没想到会这么喜欢它,但就这样发生了!",
  "voice": "Zephyr (Female)",
  "voice_prompt": "兴奋、随意、像和朋友聊天一样的真实语气",
  "video_prompt": "此人正在房间里随意对着相机说话,自然的手势",
  "resolution": "1080p"
}'

为什么选择 P-Video-Avatar 做 UGC

  • 全合一—内置 TTS 意味着无需独立的音频生成步骤
  • 30 种声音、10 种语言—匹配您的目标受众
  • 语音 + 视频提示—独立控制语气、情感、肢体语言和背景
  • 快 18 倍、便宜 6 倍—与 Fabric/OmniHuman/HeyGen 相比,可大规模生产 UGC
  • 1080p 支持—从单个肖像图像即可生成平台就绪的竖屏视频

批量 UGC:同一产品,多个主持人

# 生成 3 个不同的主持人
for voice in "Zephyr (Female)" "Puck (Male)" "Aoede (Female)"; do
  belt app run pruna/p-video-avatar --input "{
    \"image\": \"https://portrait.jpg\",
    \"voice_script\": \"这款产品完全改变了我的晨间习惯。五分钟就搞定了。\",
    \"voice\": \"$voice\",
    \"voice_prompt\": \"随意、真实,像一个真实的推荐\",
    \"video_prompt\": \"此人在明亮的厨房里对着相机说话\",
    \"resolution\": \"1080p\"
  }"
done

用例

  • UGC 与营销:产品演示、带 AI 主持人的 UGC 风格广告
  • 教育:课程视频、讲解视频
  • 本地化:从一张图像开始,跨 10 种语言配音内容
  • 社交媒体:一致的虚拟网红内容
  • 企业:培训视频、公告
  • 游戏:角色头像、NPC 对话

提示

  • 使用高质量肖像照片(正面、光线良好)
  • 音频应清晰,背景噪音最小
  • P-Video-Avatar 支持内置 TTS—无需独立的语音生成步骤
  • P-Video-Avatar 输出宽高比与输入图像匹配
  • 使用 pruna/p-image 以 9:16 宽高比生成竖屏视频肖像
  • OmniHuman 1.5 支持单张图像中的多个人物
  • LatentSync 最适合将现有视频同步到新音频

相关技能

# 专用 P-Video-Avatar 技能
npx skills add inference-sh/skills@p-video-avatar

# 完整平台技能(所有 250+ 应用)
npx skills add inference-sh/skills@infsh-cli

# 文本到语音(为非 TTS 头像模型生成音频)
npx skills add inference-sh/skills@text-to-speech

# 语音到文本(为配音进行转写)
npx skills add inference-sh/skills@speech-to-text

# 视频生成
npx skills add inference-sh/skills@ai-video-generation

# 图像生成(创建头像图像)
npx skills add inference-sh/skills@ai-image-generation

浏览所有视频应用:belt app store --category video

文档

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 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

Download YouTube videos, extract/proofread/translate subtitles, and render them onto video. Use whenever the user asks to download a YouTube video with subtitles, translate video subtitles to Chinese, add subtitles/burn subtitles to a video, or do ASR transcription on video audio. Covers the full pipeline: video download → subtitle extraction → proofreading → translation → SRT generation → subtitle rendering. Also use for "下载视频加字幕", "视频翻译字幕", "把字幕烧录到视频中". For pure subtitle file creation without rendering (just SRT output), this skill handles that too — stop before Phase 5.

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