avatar-video
Generates talking avatar videos by chaining image generation (nano-banana), voice synthesis (MiniMax Speech via fal.ai), and lip-sync animation (OmniHuman 1.5 or Infinite Talk via fal.ai). Use when asked to "create a talking avatar", "generate a video with speech", "make an avatar say something", "lip-sync", or any video generation task combining portrait + voice + animation.
- License 许可
- MIT
- 最近更新
- 2026-11-06
- Stars
- ★ 4
- Forks
- 0
01 前言 Front Matter
- name
- avatar-video
- description
- Generates talking avatar videos by chaining image generation (nano-banana), voice synthesis (MiniMax Speech via fal.ai), and lip-sync animation (OmniHuman 1.5 or Infinite Talk via fal.ai). Use when asked to "create a talking avatar", "generate a video with speech", "make an avatar say something", "lip-sync", or any video generation task combining portrait + voice + animation.
- user-invocable
- true
02 资源文件 5
- 脚本scripts/generate-avatar.sh9.1 KB
- 脚本scripts/infinitetalk-lipsync.sh8.2 KB
- 脚本scripts/minimax-tts.sh5.2 KB
- 脚本scripts/omnihuman-lipsync.sh7.3 KB
- 脚本scripts/setup.sh3.3 KB
03 SKILL.md 正文
avatar-video
Full pipeline: text script → portrait image → voice audio → lip-synced video.
/init - First-Time Setup
~/.claude/skills/avatar-video/scripts/setup.sh
This creates ~/.avatar-video/.env with your FAL_KEY. Get one at https://fal.ai → Dashboard → API Keys.
nano-banana must also be installed (see /nano-banana skill).
Quick Reference
Full Pipeline (text → video)
# Premium quality (OmniHuman 1.5) — ~\$3.68 for 30s
~/.claude/skills/avatar-video/scripts/generate-avatar.sh \
"Hi, I'm your your app assistant. I'm here to help you navigate your VA disability claim." \
--quality premium
# Budget quality (Infinite Talk) — ~\$1.88 for 30s
~/.claude/skills/avatar-video/scripts/generate-avatar.sh \
"Welcome to our service" \
--quality budget
Individual Steps
# 1. Generate portrait (uses nano-banana)
nano-banana "professional headshot of a woman, studio lighting, neutral background" -s 1K -o portrait
# 2. Generate voice (MiniMax Speech)
~/.claude/skills/avatar-video/scripts/minimax-tts.sh \
"Hello, welcome to your app" \
--voice Friendly_Person \
--output speech.mp3
# 3a. Lip-sync with OmniHuman 1.5 (premium)
~/.claude/skills/avatar-video/scripts/omnihuman-lipsync.sh \
--image portrait.png \
--audio speech.mp3 \
--output avatar-video.mp4
# 3b. Lip-sync with Infinite Talk (budget)
~/.claude/skills/avatar-video/scripts/infinitetalk-lipsync.sh \
--image portrait.png \
--audio speech.mp3 \
--output avatar-video.mp4
Orchestrator Options
| Flag | Default | Description |
|---|---|---|
--quality |
premium |
premium (OmniHuman) or budget (Infinite Talk) |
--engine |
auto | omnihuman or infinitetalk (overrides --quality) |
--voice |
Friendly_Person |
MiniMax voice ID |
--voice-speed |
1.0 |
Speech speed (0.5-2.0) |
--image |
- | Skip image gen, use existing portrait |
--audio |
- | Skip voice gen, use existing audio |
--output |
avatar-{timestamp} |
Output filename (no extension) |
--dir |
current directory | Output directory |
--image-prompt |
auto | Custom prompt for portrait generation |
MiniMax Speech Voices
Built-in voices (pass to --voice):
| Voice ID | Description |
|---|---|
Wise_Woman |
Mature, authoritative female |
Friendly_Person |
Warm, approachable (default) |
Deep_Voice_Man |
Deep, resonant male |
Calm_Woman |
Soothing, relaxed female |
Casual_Guy |
Informal, conversational male |
Lively_Girl |
Energetic, youthful female |
Custom voice cloning: provide a voice sample URL as --voice <url_to_6sec_sample>.
Engine Comparison
| Feature | OmniHuman 1.5 | Infinite Talk |
|---|---|---|
| Cost | $0.12/s (lip-sync) | $0.03/s (480p), $0.06/s (720p) |
| 30s video | ~$3.60 | ~$0.90-$1.80 |
| Max length | 30s audio | 10 minutes |
| Quality | Best — full body motion, gestures | Good — solid lip-sync |
| Resolution | 720p/1080p | 480p/720p |
| Best for | Short premium content, ads | Long-form, bulk, prototyping |
Full Pipeline Costs (30-second video)
| Step | Tool | Cost |
|---|---|---|
| Image | nano-banana (Gemini Flash) | ~$0.05 |
| Voice | MiniMax Speech 2.6 Turbo | ~$0.03 |
| Lip-sync (budget) | Infinite Talk 720p | ~$1.80 |
| Lip-sync (premium) | OmniHuman 1.5 | ~$3.60 |
| Total (budget) | ~$1.88 | |
| Total (premium) | ~$3.68 |
Cost Tracking
Every generation logs to ~/.avatar-video/costs.json. View summary:
~/.claude/skills/avatar-video/scripts/generate-avatar.sh --costs
API Keys
| Service | Key | Source |
|---|---|---|
| MiniMax Speech, OmniHuman, Infinite Talk | FAL_KEY |
~/.avatar-video/.env |
| nano-banana (image gen) | GEMINI_API_KEY |
~/.nano-banana/.env |
All fal.ai services use a single key. Get one at https://fal.ai.
Troubleshooting
- "FAL_KEY not found" — Run setup:
~/.claude/skills/avatar-video/scripts/setup.sh - "Audio must be under 30s" (OmniHuman) — Use Infinite Talk for longer audio, or trim script
- Upload failed — Check FAL_KEY is valid; fal.ai file upload requires auth
- Queue timeout — OmniHuman can take 2-5 min; the script polls automatically
- nano-banana not found — Install via
/nano-bananaskill init
04 同仓库更多 Skills
zi-search
暂无简介
visualise
Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial/interactive diagram rather than text. Also triggers for: flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and any request containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'. Even when the user doesn't explicitly ask for a visual, use this skill proactively when the topic has spatial, sequential, or systemic relationships that a diagram would clarify better than prose.
video
When the user wants to create, generate, or produce video content using AI tools or programmatic frameworks. Also use when the user mentions 'video production,' 'AI video,' 'Remotion,' 'Hyperframes,' 'HeyGen,' 'Synthesia,' 'Veo,' 'Runway,' 'Kling,' 'Pika,' 'video generation,' 'AI avatar,' 'talking head video,' 'programmatic video,' 'video template,' 'explainer video,' 'product demo video,' 'video pipeline,' or 'make me a video.' Use this for video creation, generation, and production workflows. For video content strategy and what to post, see social-content. For paid video ad creative, see ad-creative.
manim-video
Production pipeline for mathematical and technical animations using Manim Community Edition. Creates 3Blue1Brown-style explainer videos, algorithm visualizations, equation derivations, architecture diagrams, and data stories. Use when users request: animated explanations, math animations, concept visualizations, algorithm walkthroughs, technical explainers, 3Blue1Brown style videos, or any programmatic animation with geometric/mathematical content.
video-use
Edit any video by conversation. Transcribe, cut, color grade, generate overlay animations, burn subtitles — for talking heads, montages, tutorials, travel, interviews. No presets, no menus. Ask questions, confirm the plan, execute, iterate, persist. Production-correctness rules are hard; everything else is artistic freedom.
ui-improver
暂无简介