AI Video Models by GetRun · Rp20 / second output · about 20 to 180 seconds · available now
Assemble several clips into one vertical video: cut each segment to the timeline, match ratio and frame rate, then burn in captions. It runs on GetRun servers and is not a generative model — it never adds or alters any imagery.
Capabilities
Cut per segment
Burned-in captions
Matches ratio & frame rate
Sample output
Sample output from GetRun Assemble, made on GetRun.
Input parameters
Name
Type
Required
fps
24 | 25 | 30
no
clips
array
yes
seconds
number
yes
timeline
string
yes
resolution
720p | 1080p
no
aspect_ratio
9:16 | 16:9 | 1:1
no
The complete schema is published as JSON Schema at GET https://getrun.id/v1/models.
How to call it through the API
Try GetRun Assemble in Studio, or call it from code: POST https://getrun.id/v1/tasks with body {"model": "getrun-edit/assemble", "input": {…}} and an Idempotency-Key header, then poll GET https://getrun.id/v1/tasks/{task_id}. The details are in the model documentation.
GetRun Assemble is priced at Rp20 / second output and billed from a rupiah balance as you use it, with no required subscription. The estimated cost is shown before it runs, and failed tasks are never charged.
How do I call GetRun Assemble through the API?
Send POST https://getrun.id/v1/tasks with an Authorization: Bearer header and an Idempotency-Key, body {"model": "getrun-edit/assemble", "input": {...}}, then poll GET https://getrun.id/v1/tasks/{task_id} every 2 to 5 seconds until the status is succeeded.
How long does GetRun Assemble take per request?
GetRun Assemble typically takes 20 to 180 seconds, depending on load and the input parameters.
Are GetRun Assemble results stored permanently?
No. Output URLs are served from a CDN and expire after 7 days, so copy the files to your own storage if you need them longer.