CLI

npm install -g @creatorline/cli
crl auth login          # paste a key from Settings → API

Zero runtime dependencies, Node 20+. Grammar is always crl <command> <subcommand>.

The three-line version

crl accounts use Eda
crl gen create text-to-photo --prompt "matcha latte flatlay" --wait --output-dir ./out
crl posts create --asset <asset-id> --caption "morning ritual ☕️" --publish now

Commands

Command	Subcommands
`auth`	`login`, `logout`, `whoami`
`models`	`list [tool]`, `get <model-id>`
`voices`	`list`
`accounts`	`list`, `use <id\|name>`, `current`, `clear`
`gen`	`create <tool>`, `cost <tool>`, `get <id>`, `wait <id>`, `list`
`posts`	`create`, `publish <id>`, `list`, `get <id>`
`assets`	`list`, `get <id>`
`upload`	`crl upload <file>`
`credits`	—
`mcp`	`config`, `install`

generate aliases gen, creators aliases accounts, clips aliases posts.

Global flags

Flag	Default
`--json`		machine-readable output, and nothing else on stdout
`--wait`		block until the generation finishes
`--wait-timeout`	`10m`	give up waiting — the run continues server-side
`--wait-interval`	`3s`	poll interval
`--output-dir`		download results to disk
`--api-key`, `--api-url`		override the stored credentials
`--no-color`, `--help`, `--version`

Both spellings of every flag work. --aspect-ratio and --aspect_ratio are the same flag. Model parameters are snake_case and CLI convention is kebab-case; guessing wrong should not be a failure mode.

The model’s flags are the model’s schema

crl gen create fetches the model’s schema first, then interprets the remaining flags against it. The CLI hardcodes no model parameters, so a new model works the day it ships:

crl models get bytedance-seedance-2-0-reference-to-video-fast
crl gen create ugc-video --prompt "unboxing" --image ./face.png --duration 5 --wait

A wrong flag tells you the fix:

error Unknown flag --durations for model bytedance-seedance-2-0-reference-to-video-fast.
  inputs:     --characters --location --objects --audio_urls
  parameters: --ugc_style --aspect_ratio --duration --resolution --generate_audio
  Run `crl models get bytedance-seedance-2-0-reference-to-video-fast` for values and defaults.

crl models get <id> prints the whole schema: each input’s modality and cap, each parameter’s allowed values or numeric bounds, what opaque values like caption styles mean, whether a prompt is required, and the model’s take length.

Media flags take a path or an id

--image ./face.png uploads the file and uses it. --image <asset-id> reuses an existing asset. --image https://… passes the URL through. No separate upload step — though crl upload <file> exists when you want to pin an id. Prompts can come from stdin:

echo "a cinematic city at dusk" | crl gen create text-to-photo --wait

Run flags that are not model parameters

Flag
`--source-url <url>`	work from a video link instead of a file, for a tool that takes one (`short-clip`). A bare URL positional does the same: `crl gen create short-clip https://youtu.be/…`
`--no-account-avatar`	keep the selected creator out of the output (a product shot on their account)
`--voice_id`, `--voice_a`, `--voice_b`	a voice from `crl voices list` — otherwise the creator’s own cloned voice is used

crl gen create short-clip https://youtu.be/xyz --wait --output-dir ./shorts
crl voices list --scope library --search "warm female" --language en
crl gen create text-to-speech --prompt "hey, welcome back" --voice_id <voice-id> --wait

Price a source-billed run with its media. lipsync, motion-control, scene-video, change-voice and short-clip are billed per second of the source. crl gen cost passes along any asset id, URL or --source-url you give it and prints the length it billed, so the quote matches the charge.

Pick a creator once

crl accounts list
crl accounts use Eda        # persisted, like the studio's creator switcher
crl accounts current

Every later gen create and posts create runs as that creator. --account-id overrides it for one command.

Post flags

crl posts create builds a post; --publish now|schedule|queue chains the send. The format follows the media — one video is a video, two or more stills are a carousel — so most posts need only --asset and --caption.

Flag
`--asset <id>`	repeatable, or comma-separated. Post order.
`--caption`, `--title`	text. The caption also comes from stdin.
`--tag ugc,fyp`	hashtags, without the `#`. Appended to the caption when sent.
`--channels TikTok,IG`	defaults to the creator’s connected channels
`--format`	`photo`, `video` or `carousel`, when you want to be explicit
`--at 21:30`, `--timezone`	scheduling
`--draft`	hand it to TikTok’s Creator Inbox instead of publishing. Every channel on the post must take drafts
`--made-with-ai`	AI disclosure, on every channel that has one (TikTok and YouTube)
`--device`	also post from the creator’s bound phone, alongside the channels
`--device-only`	post from the bound phone and nowhere else. Sends an empty channel list for you
`--no-music`	TikTok photo carousels: no soundtrack (on by default)
`--cover 1`	TikTok photo carousels: cover image, 0-based
`--yt-title`, `--yt-visibility`	YouTube title and `public\|unlisted\|private`
`--platform-settings '<json>'`	per-platform captions and times

crl posts create --asset "$A" --asset "$B" --channels TikTok --cover 1 --no-music
crl posts create --asset "$A" --channels TikTok --draft --publish now
crl posts create --asset "$A" --device-only --publish now
crl posts create --asset "$A" --platform-settings '{"TikTok":{"caption":"the short version"}}'

--draft, --made-with-ai, --device and --device-only are switches. The bare flag turns one on, and --device true and --device=true say the same thing. Leaving a switch off sends nothing at all rather than an explicit false.

Phone posting is enabled per workspace, on request, and the creator has to be bound to a device in the studio. Without both, --device and --device-only come back as an error saying which one is missing. --device cannot be combined with --draft: the phone posts directly and has no draft inbox. See Publishing for the detail.

crl posts publish asks for confirmation on a terminal when it would go live; a draft handoff says so instead of warning about a public post. Pass --yes in scripts.

Scripting and agents

Results go to stdout, progress and errors to stderr, so pipes stay clean:

crl gen list --json | jq -r '.data[] | select(.status=="succeeded") | .output[0].url'

With --wait, crl gen create prints the media URL. Without it, the generation id. Parallel fan-out is just shell job control — --wait blocks per process:

for tool in text-to-photo ugc-video; do
  crl gen create "$tool" --prompt "$PROMPT" --wait --output-dir "./out/$tool" &
done
wait

Exit codes: 0 success · 1 usage or runtime error · 2 not authenticated · 3 out of credits.

Configuration

Precedence: flags → environment → config file.


`CREATORLINE_API_KEY`	the key
`CREATORLINE_API_URL`	the API base (default `https://api.creatorline.io`)
`~/.config/creatorline/config.json`	written by `crl auth login`, mode `0600`

CI wants the environment variable — there is no interactive login there.

CREATORLINE_API_KEY=$CI_SECRET crl gen create text-to-photo --prompt "…" --wait --json

Get started

Guides

API reference

The three-line version

Commands

Global flags

The model’s flags are the model’s schema

Media flags take a path or an id

Run flags that are not model parameters

Pick a creator once

Post flags

Scripting and agents

Configuration

​The three-line version

​Commands

​Global flags

​The model’s flags are the model’s schema

​Media flags take a path or an id

​Run flags that are not model parameters

​Pick a creator once

​Post flags

​Scripting and agents

​Configuration

The three-line version

Commands

Global flags

The model’s flags are the model’s schema

Media flags take a path or an id

Run flags that are not model parameters

Pick a creator once

Post flags

Scripting and agents

Configuration