Text Overlay
Text Overlay puts one line of copy on a finished clip. The copy shows as white text in a dark, rounded card. You set the position and the time window. The clip keeps its own sound.
assembly · model text-overlay · catalog model-catalog@2026-10-06.v5 · pricing customer-pricing@2026-11-05.v15.Endpoint
POST https://api.roasos.com/v1/assembly/text-overlaySend your API key as a bearer token. The key needs the scope api:write. Every paid request also needs an Idempotency-Key header.
The envelope fields quote_only, quote_id, webhook_url and wait_timeout_seconds behave the same on each model endpoint. Refer to Jobs and Quotes and credits.
Good at
Use it for copy that the clip does not say: a hook, an offer, a claim or a call to action. Captions show only the spoken words. Use this operation for all other on-screen text.
The price is three credits, flat. The length of the clip does not change the price.
Pricing
The unit is one operation. Pricing key: text-overlay.
| Request | Credits |
|---|---|
per_operation | 3 |
The credits come from the roasOS pricing table. No other field changes the price. To get the exact price of your request, send it with quote_only: true first.
Modes
text-overlay
Provider endpoints: fal-ai/workflow-utilities/blend-video.
Request fields
| Field | Type | Required | Default | Rule |
|---|---|---|---|---|
end_seconds | number | no | — | 0–180 |
position | enum | no | top | top, center, bottom |
quote_id | string | no | — | UUID |
quote_only | boolean | no | false | — |
start_seconds | number | no | 0 | 0–180 |
text | string | yes | — | ≥ 1 character; ≤ 120 characters |
video_url | string | yes | — | https URL; ≤ 4,096 characters |
wait_timeout_seconds | integer | no | 0 | 0–60 |
webhook_url | string | no | — | https URL; ≤ 4,096 characters |
The schema is strict. A field that is not in this table gets 400 unsupported_option. The field names are the roasOS role names. One role has one name in every family.
Media
This endpoint accepts these media roles:
video_url— the source video
| Role | Items | Maximum size | Content types | Duration |
|---|---|---|---|---|
video_url | ≤ 1 | 100 MB | video/mp4 | 0–180 s |
Every other role is refused: avatar_id, elements, product_id, product_images, references, reference_images, image_url, end_image_url, scene_id, scene_image, video_urls, audio_urls, audio_url, voice_id. A refused role gets 400 unsupported_option.
https://cdn.roasos.com that your workspace owns. Any other URL gets 400 reference_media_not_workspace_owned. Refer to Reference media and uploads to learn how to put a file there.Prompt
None. This operation takes no prompt.
text is the exact copy. It is plain text of 120 characters or fewer. Short lines of 3 to 8 words are easiest to read. Emoji are removed, because they can change the colour of the video below them.
position is top, center or bottom. The default is top. The top position is below the status bar. The bottom position is above the caption and button area of a social feed. Do not put the card on the product or on the face of the speaker.
start_seconds and end_seconds set when the copy shows. The default window is the full clip. end_seconds must be after start_seconds. If start_seconds is after the end of the clip, the job fails and you get the credits back. To show two lines, for example a hook and then a call to action, run the operation two times. Use the output of the first run as the input of the second run.
Add text after you trim and join clips, and before you add captions. Each step makes the full file again.
Not exposed
These catalog entries describe omitted inputs, pinned values and source constraints. They do not imply that the provider accepts every listed field.
blend_mode— pinned tograinmerge.opacity— pinned to1.shortest— pinned totrue.
Result
The result kind is video. Always present: url.
{
"data": {
"id": "gen_…",
"kind": "video",
"model": "text-overlay",
"status": "completed",
"result": {
"url": "https://cdn.roasos.com/workspaces/ws_01/result"
}
}
}The files are immutable objects on https://cdn.roasos.com. A result URL is a valid media input for your next request.
Example
The three steps are always the same: quote, run, poll.
# 1. Quote. Nothing is spent.
curl -X POST https://api.roasos.com/v1/assembly/text-overlay \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-text-overlay-0001" \
-H "Content-Type: application/json" \
-d '{"quote_only":true,"text":"Two drops, morning and night. That is the whole routine.","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 3, "expires_at": "...",
# "confirmation": { "model": "text-overlay", "example": "per_operation" } } }
# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/assembly/text-overlay \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-text-overlay-0001" \
-H "Content-Type: application/json" \
-d '{"quote_id":"q_7Hk...","text":"Two drops, morning and night. That is the whole routine.","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 201 { "data": { "id": "gen_...", "status": "queued", "credits_reserved": 3 } }
# 3. Poll, then read the result.
curl https://api.roasos.com/v1/jobs/gen_.../status -H "Authorization: Bearer roasos_sk_live_..."
curl https://api.roasos.com/v1/jobs/gen_.../result -H "Authorization: Bearer roasos_sk_live_..."Today
The endpoint is POST /v1/assembly/text-overlay.
It is live.
See also
llms.txtfor this model — the same facts as one plain-text file for an agent.GET https://api.roasos.com/v1/catalog/text-overlay— the machine-readable form: enums, defaults, limits and prices. Refer to the API reference.- Jobs — how to poll a job and read its result.
- Provider endpoints:
fal-ai/workflow-utilities/blend-video.