roasOS
ModelsCaptions

VEED Subtitles

VEED Subtitles transcribes the speech in a clip and burns styled subtitles into it. It returns a rendered, delivery-ready video and no timing data.

Family captions · model veed-subtitles · catalog model-catalog@2026-10-06.v5 · pricing customer-pricing@2026-11-05.v15.

Endpoint

POST https://api.roasos.com/v1/captions/veed-subtitles

Send 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

Ship captions on a finished ad. Pick a preset: it sets the fonts, colours, layout and animation, and it also sets the price. Nine of the thirty presets are dynamic and cost double; the other twenty-one are basic and cost the base rate.

The price is $0.10 for each minute of the SOURCE clip, with a one-minute minimum. A dynamic preset doubles it. A source above 1080p on its short side doubles it again. A translation_language adds a flat $0.20 per minute on top. The worst case is $0.60 per minute — six times the base — so read the quote before you confirm.

roasOS measures the source before it quotes. The source must be 480 seconds or shorter. When the length or the resolution cannot be measured, the request is refused; roasOS never assumes the cheap tier.

Pricing

The unit is one source_minute. Pricing key: veed-subtitles.

RequestCredits
30s_source2
60s_source2
120s_source3
60s_source_dynamic_preset3
60s_source_worst_case8

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

  • subtitle

Provider endpoints: veed/subtitles.

Request fields

FieldTypeRequiredDefaultRule
languagestringno—≥ 2 characters; ≤ 35 characters
positionenumno—top, center, bottom
presetenumyes—glass, whisper, glide2, fusion, glide, terminal, handwritten, backdrop, backdrop2, simple, plain, beans, corpo, boo, shadeplay, casper, capri, lowkey, vinta, diego, ali, slay, kitty, hustle, karl, sprout, flex, mint, rizz, vegas
quote_idstringno—UUID
quote_onlybooleannofalse—
translation_languagestringno—≥ 2 characters; ≤ 35 characters
video_urlstringyes—https URL; ≤ 4,096 characters
vocabularyobject[]no—1–100 items; each { word, replaces }
wait_timeout_secondsintegerno00–60
webhook_urlstringno—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
RoleItemsMaximum sizeContent typesDuration
video_url≤ 1100 MBvideo/mp40–480 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.

Each media URL must be an immutable object on 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 model takes no prompt.

Pick preset deliberately; it is the one field that changes both the look and the bill. Set language only when the source is hard to detect. Set translation_language only when you want the captions in a different language from the speech.

Not exposed

These catalog entries describe omitted inputs, pinned values and source constraints. They do not imply that the provider accepts every listed field.

  • srt_content — not accepted by this public endpoint.
  • srt_file_url — not accepted by this public endpoint.
  • customization.shadow — not accepted by this public endpoint.
  • customization.text_customizations — not accepted by this public endpoint.

Result

The result kind is video. Always present: url.

{
  "data": {
    "id": "gen_…",
    "kind": "video",
    "model": "veed-subtitles",
    "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/captions/veed-subtitles \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-veed-subtitles-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_only":true,"preset":"glass","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 2, "expires_at": "...",
#        "confirmation": { "model": "veed-subtitles", "example": "30s_source" } } }

# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/captions/veed-subtitles \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-veed-subtitles-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_id":"q_7Hk...","preset":"glass","video_url":"https://cdn.roasos.com/workspaces/ws_01/uploads/video_url.mp4"}'
# 201 { "data": { "id": "gen_...", "status": "queued", "credits_reserved": 2 } }

# 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/captions/veed-subtitles.

It is live.

See also

  • llms.txt for this model — the same facts as one plain-text file for an agent.
  • GET https://api.roasos.com/v1/catalog/veed-subtitles — 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: veed/subtitles.

On this page