
Seedance Cli
Generate AI video via the Seedance model from the command line.
Install
npx skills add https://github.com/vaxin/seedance-cli --skill seedance-cliWhat is this skill?
- Seedance video generation
- CLI tooling
- AI video
Adoption & trust: 1 installs on skills.sh; 2/3 security scanners passed (skills.sh audits); trending (+100% hot-view momentum).
Recommended Skills
Video Editagentspace-so/runcomfy-agent-skills
Image To Videoagentspace-so/runcomfy-agent-skills
Image Editagentspace-so/runcomfy-agent-skills
Flux Kontextagentspace-so/runcomfy-agent-skills
Nano Banana 2agentspace-so/runcomfy-agent-skills
Nano Banana Editagentspace-so/runcomfy-agent-skills
Journey fit
Common Questions / FAQ
Is Seedance Cli safe to install?
skills.sh reports 2 of 3 security scanners passed. Review the Security Audits panel on this page before installing in production.
SKILL.md
READMESKILL.md - Seedance Cli
# seedance-cli Command-line interface for **Seedance 2.0** video generation on Volcengine Ark. Binary name: `seedance`. Written in Rust. Config stored at `~/.config/seedance/config.toml`. Task history in local SQLite at `~/.config/seedance/tasks.db`. --- ## Quick Start ```bash # 1. Configure API key (interactive) seedance config init # 2. Generate a video (text-to-video) seedance generate "A cat sits on a windowsill watching rain fall outside" # 3. Generate and wait for result seedance generate "Sunset over mountain lake, slow drone pullback" --wait # 4. Generate with full control seedance generate "Product bottle on marble surface, slow orbit" \ --model standard --duration 8 --ratio 16:9 --resolution 1080p --wait ``` --- ## Installation ```bash # From source cargo install --path . # Verify seedance --version ``` --- ## Environment | Variable | Purpose | | ------------- | -------------------------------------- | | `ARK_API_KEY` | API key (overrides config file if set) | Priority: `ARK_API_KEY` env var > `config.toml` api_key. --- ## Commands ### `seedance generate` — Create a Video The core command. Supports T2V, I2V, V2V, and R2V workflows. ``` seedance generate <PROMPT> [OPTIONS] ``` **PROMPT** can be a literal string or `@file.txt` to read from a file. #### Generation Options | Flag | Short | Default | Description | | --------------------- | ----- | ---------- | ------------------------------------------------------------ | | `--model` | `-m` | `standard` | Model variant: `standard` or `fast` | | `--duration` | `-d` | `5` | Duration in seconds (4–15) | | `--ratio` | `-r` | `16:9` | Aspect ratio (`16:9` `9:16` `4:3` `3:4` `21:9` `1:1` `adaptive`) | | `--resolution` | | `1080p` | Resolution (`480p` `720p` `1080p`) | | `--seed` | | | Random seed for reproducibility | | `--watermark` | | `false` | Add watermark | | `--audio-gen` | | `false` | Enable native audio generation | | `--return-last-frame` | | `false` | Return the last frame as an image | | `--callback` | | | Webhook callback URL | | `--web-search` | | `false` | Enable web search tool (text-only input) | | `--service-tier` | | | Service tier: `flex` for offline inference | #### Material Inputs (I2V / V2V / R2V) | Flag | Short | Repeatable | Max | Description | | --------------- | ----- | ---------- | --- | ----------------------------------- | | `--image` | `-i` | Yes | 9 | Image reference (URL or local path) | | `--video` | `-v` | Yes | 3 | Video reference (URL or local path) | | `--audio` | `-a` | Yes | 3 | Audio reference (URL or local path) | | `--first-frame` | | No | 1 | First frame image (role: `first_frame`) | | `--las