AI Video Generation

Generate videos with 30+ AI models via SkillsRouter CLI.

Quick Start

# Install CLI
curl -fsSL https://cli.skillsrouter.sh | sh && sr login

# Generate a video with Veo
sr app run google/veo-3-1-fast --input '{"prompt": "drone shot flying over a forest"}'

Install note: The install script only detects your OS/architecture, downloads the matching binary, and verifies its SHA-256 checksum. No elevated permissions or background processes.

Available Models

Text-to-Video

Model	App ID	Best For
Veo 3.1 Fast	google/veo-3-1-fast	Fast, with optional audio
Veo 3.1	google/veo-3-1	Best quality, frame interpolation
Veo 3	google/veo-3	High quality with audio
Veo 3 Fast	google/veo-3-fast	Fast with audio
Veo 2	google/veo-2	Realistic videos
Grok Video	xai/grok-video	xAI, configurable duration
Seedance 1.5 Pro	bytedance/seedance-1-5-pro	First-frame control
Seedance 1.0 Pro	bytedance/seedance-1-0-pro	Up to 1080p
Kling 2.1	kling/kling-2-1	Cinematic, long form
MiniMax Video	minimax/video-01	Creative, stylized

Image-to-Video

Model	App ID	Best For
Wan 2.5	wan/wan-2-5	Animate any image
Wan 2.5 I2V	wan/wan-2-5-i2v	High quality i2v
Seedance Lite	bytedance/seedance-1-0-lite	Lightweight 720p
Kling I2V	kling/kling-2-1-i2v	Image animation

Avatar / Lipsync

Model	App ID	Best For
OmniHuman 1.5	bytedance/omnihuman-1-5	Multi-character
OmniHuman 1.0	bytedance/omnihuman-1-0	Single character
Fabric 1.0	fabric/fabric-1-0	Image talks with lipsync
PixVerse Lipsync	pixverse/lipsync	Realistic lipsync

Utilities

Tool	App ID	Description
HunyuanVideo Foley	hunyuan/foley	Add sound effects to video
Topaz Upscaler	topaz/video-upscaler	Upscale video quality
Media Merger	skillsrouter/media-merger	Merge videos with transitions
Caption Video	skillsrouter/caption-video	Auto-generate captions
Audio Extractor	skillsrouter/audio-extract	Extract audio from video

Browse All Video Apps

sr app list --category video

Examples

Text-to-Video with Veo

sr app run google/veo-3-1-fast --input '{
  "prompt": "A timelapse of a flower blooming in a garden, soft natural light"
}'

Cinematic Scene

sr app run google/veo-3-1 --input '{
  "prompt": "sweeping aerial shot of mountain ranges at sunrise, golden hour, cinematic 4K",
  "duration": 8
}'

Grok Video

sr app run xai/grok-video --input '{
  "prompt": "Waves crashing on a beach at sunset, slow motion",
  "duration": 5
}'

Social Media (Vertical)

sr app run google/veo-3-1-fast --input '{
  "prompt": "aesthetic coffee shop scene, steam rising from a latte, warm tones",
  "aspect_ratio": "9:16"
}'

Image-to-Video with Wan 2.5

sr app run wan/wan-2-5 --input '{
  "image_url": "https://your-image.jpg",
  "prompt": "gentle camera zoom, soft breeze moving the hair"
}'

Seedance with First Frame

sr app run bytedance/seedance-1-5-pro --input '{
  "prompt": "a woman walking through a futuristic city at night",
  "first_frame_url": "https://keyframe.jpg"
}'

AI Avatar / Talking Head

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

Fabric Lipsync

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

Video Upscaling

sr app run topaz/video-upscaler --input '{
  "video_url": "https://low-res-video.mp4"
}'

Add Sound Effects (Foley)

sr app run hunyuan/foley --input '{
  "video_url": "https://silent-video.mp4",
  "prompt": "footsteps on gravel, birds chirping, wind in trees"
}'

Add Captions

sr app run skillsrouter/caption-video --input '{
  "video_url": "https://video.mp4",
  "language": "en"
}'

Merge Videos

sr app run skillsrouter/media-merger --input '{
  "videos": ["https://clip1.mp4", "https://clip2.mp4"],
  "transition": "fade"
}'

Workflow Tips

1. Storyboard with images first: Use nano-banana to generate key frames, then animate with image-to-video
2. Add narration: Generate speech with kokoro-tts, then use omnihuman for talking head
3. Post-process: Upscale with topaz, add foley sound, merge clips, add captions
4. Iterate on prompts: Start simple, add detail progressively
5. Check task status: Video generation takes longer — use sr task get <task-id>

Complete Video Pipeline Example

# 1. Generate a key frame
sr app run google/nano-banana --input '{
  "prompt": "a futuristic cityscape at night, neon lights, rain-slicked streets"
}'

# 2. Animate the image
sr app run wan/wan-2-5 --input '{
  "image_url": "OUTPUT_FROM_STEP_1",
  "prompt": "slow camera pan, rain falling, reflections on wet ground"
}'

# 3. Generate narration
sr app run kokoro/tts --input '{
  "text": "In the year 2077, the city never sleeps...",
  "voice": "warm"
}'

# 4. Add sound effects
sr app run hunyuan/foley --input '{
  "video_url": "OUTPUT_FROM_STEP_2",
  "prompt": "rain, distant traffic, neon buzzing"
}'

# 5. Merge narration with video
sr app run skillsrouter/media-merger --input '{
  "video_url": "OUTPUT_FROM_STEP_4",
  "audio_url": "OUTPUT_FROM_STEP_3"
}'

Related Skills

# Full platform skill (all 50+ apps)
npx skills add skillsrouter/skills@agent-tools

# Google Veo specific
npx skills add skillsrouter/skills@veo-video

# Image generation (for storyboarding / key frames)
npx skills add skillsrouter/skills@ai-image-generation
npx skills add skillsrouter/skills@nano-banana

# Text-to-speech (for video narration)
npx skills add skillsrouter/skills@kokoro-tts

# Web search (for research / content ideas)
npx skills add skillsrouter/skills@web-search

Browse all apps: sr app list

Documentation

• SkillsRouter Docs - Getting started
• Running Apps - How to run apps via CLI
• Video Generation Guide - Best practices
• Content Pipeline - Building media workflows