Gemini Omni Flash UGC

Endpoint

POST https://api.roasos.com/v1/ugc/gemini-omni-flash

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

A fast talking-head UGC clip and a reference-led composition. It is the default model of the UGC talking-head role in roasos_get_catalog. Reference mode holds a saved person and a saved product together well. The clip is 3 to 15 seconds at 360p, 720p, 1080p or 4k (720p by default). The model adds synchronized sound and lip-syncs the script. You cannot send a voice file. For a clip longer than 15 seconds, use a Seedance lane.

Pricing

The unit is one clip. Pricing key: gemini-omni-flash.

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

• standard
• reference

roasOS selects the mode from the media fields of your request. You do not send a mode.

Provider endpoints: google/gemini-omni-flash/v1.2/image-to-video · google/gemini-omni-flash/v1.2/reference-to-video.

Request fields

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:

• avatar_id — identity; the saved character reference sheet, with a derived portrait only where the model requires a single face or source frame
• product_id — product; resolves to the product image list
• references — style and appearance references
• scene_id — first frame — a scene this workspace owns
• scene_image — first frame — a CDN image

Every other role is refused: elements, product_images, reference_images, image_url, end_image_url, video_urls, video_url, audio_urls, audio_url, voice_id. A refused role gets 400 unsupported_option.

Prompt

• Standard mode: the worker appends the UGC facts block ("Use the supplied first frame … The requested format is a UGC video ad; preserve the supplied script/action …") to the script.
• Reference mode: no facts block. Write no @Image tags yourself; the worker binds every reference.
• Write the words to be spoken in quotes: says exactly with warm energy: "…".
• Describe motion as physics: "Realistic hand movements, she lifts the jar to chest height."
• Anchor the hands to an object. A contact point holds hands and fabric better.
• Use a static camera for a talking head. Use one subject and one action for each clip.
• Do not write claims, camera moves or music that the product does not have.

Not exposed

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

• duration_seconds — these values are not available: 3, 4, 6, 7, 9.
• prompt — pinned to characters 10,001–20,000.
• generate_audio — pinned to always on; no switch and no audio-off price.
• seed — not accepted by this public endpoint.
• negative_prompt — not accepted by this public endpoint.
• cfg_scale — not accepted by this public endpoint.
• shot_type — not accepted by this public endpoint.
• multi_prompt — not accepted by this public endpoint.
• video_url — not accepted by this public endpoint.
• end_image_url — not accepted by this public endpoint.
• video_urls — not accepted by this public endpoint.

Result

The result kind is ugc. Always present: url.

{
  "data": {
    "id": "gen_…",
    "kind": "ugc",
    "model": "gemini-omni-flash",
    "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/ugc/gemini-omni-flash \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-gemini-omni-flash-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_only":true,"script":"Two drops, morning and night. That is the whole routine."}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 3, "expires_at": "...",
#        "confirmation": { "model": "gemini-omni-flash", "example": "3s_720p" } } }

# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/ugc/gemini-omni-flash \
  -H "Authorization: Bearer roasos_sk_live_..." \
  -H "Idempotency-Key: 0f1c9e2a-gemini-omni-flash-0001" \
  -H "Content-Type: application/json" \
  -d '{"quote_id":"q_7Hk...","script":"Two drops, morning and night. That is the whole routine."}'
# 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 app route POST /api/generate/ugc-ads { sceneId | sceneImage, script, model: "gemini-omni-flash", async: true } sends the same request. Use this endpoint instead: 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/gemini-omni-flash — 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: google/gemini-omni-flash/v1.2/image-to-video · google/gemini-omni-flash/v1.2/reference-to-video.