> ## Documentation Index > Fetch the complete documentation index at: https://docs.gengen.farm/llms.txt > Use this file to discover all available pages before exploring further. # Generate and edit videos with Omni > Google Gemini Omni Flash and Omni 1.1 Flash video generation. Use `gemini-omni-1.1-flash-preview` or `gemini-omni-flash-preview` under Google. Both are Preview models and return asynchronous video tasks with native audio. ## Create and retrieve ```bash theme={"dark"} curl https://gengen.farm/v1/contents/generations/tasks \ -H 'Authorization: Bearer gengen_live_xxxxxxxxxxxxxxxx' \ -H 'Content-Type: application/json' \ -d '{ "model": "gemini-omni-1.1-flash-preview", "mode": "text_to_video", "prompt": "An ocean sunrise with gentle surf sounds.", "controls": {"duration": 5, "resolution": "720p", "ratio": "16:9"} }' ``` Save the returned `id`, including `omni:`, and poll the [shared task endpoint](/api-reference/google/omni-retrieve-task) with the same API key until `succeeded` or `failed`. Read `outputs.videos` on success. Each creation request creates a new task; polling never resubmits generation. ```bash theme={"dark"} curl 'https://gengen.farm/v1/contents/generations/tasks/omni:YOUR_TASK_UUID' \ -H 'Authorization: Bearer gengen_live_xxxxxxxxxxxxxxxx' ``` ## Modes | Mode | Assets | Omni Flash | Omni 1.1 Flash | | - | - | - | - | | `text_to_video` | None | Yes | Yes | | `video_modify` | `sourceVideo` | Yes | Yes | | `image_first_frame` | `firstFrameImage` | No | Yes | | `image_first_last_frame` | `firstFrameImage`, `lastFrameImage` | No | Yes | | `multimodal_reference` | `referenceImages`, `referenceVideos` | No | Yes | | `video_extend` | `sourceVideo` | No | Yes | Mode is inferred when omitted; a source video defaults to editing. Set `video_extend` explicitly to extend. Do not combine frames, references and source-video input forms. Audio input and image output are unsupported. ```json theme={"dark"} { "model": "gemini-omni-1.1-flash-preview", "mode": "image_first_last_frame", "prompt": "Move smoothly from the first frame to the last frame.", "assets": { "firstFrameImage": "https://example.com/start.png", "lastFrameImage": "https://example.com/end.png" }, "controls": {"duration": 5, "resolution": "1080p", "ratio": "16:9"} } ``` ## Limits and controls * `prompt`: 1–10,000 characters. * `duration`: requested duration, integer 3–10 seconds; default 5. Actual output and billable token usage may differ. * `resolution`: Omni Flash supports `720p`. Omni 1.1 adds `360p`, `1080p` and `4k`. * `ratio`: `16:9` or `9:16`; default `16:9`. * One video per task. `outputCount`, if supplied, must be 1. Playground can submit several independent tasks. * Native audio is always enabled. `generateAudio`, if supplied, must be `true`. * Up to 10 reference images and 3 reference videos. Images accept JPEG/PNG/WebP over HTTPS (JPEG/PNG for GCS), up to 20 MiB each. Converted PNG must also fit this limit. Videos accept MP4 up to 64 MiB and 10 seconds each. Use public/signed HTTPS URLs or account-authorized `gs://` objects. GCS access requires both caller authorization and storage read permissions; contact support to register an external object or directory. Base64, local paths and `asset://` inputs are unsupported. Media is validated before upstream generation; invalid media fails the task and releases its reservation. ## Billing and outputs Billing combines input tokens, text/reasoning tokens and video output tokens. See [current prices](/pricing). A conservative maximum reservation covers generation; final settlement uses actual returned token usage and releases the unused reservation. A requested duration alone does not determine the final price. Video links are temporary HTTPS URLs, retained for seven days after completion. Retrieve the task to renew a link before retention expires, or copy it to your own storage. Listing owned tasks is supported. This GENGEN endpoint does not expose cancellation, deletion, webhooks, streaming, or conversational interaction IDs. Invalid or unsupported parameters return HTTP 400 before reservation. Insufficient balance returns 402. A task whose upstream acceptance is uncertain remains pending for reconciliation; retrieve it rather than submitting a duplicate. ## OpenAPI ````yaml openapi/omni-video.yaml POST /contents/generations/tasks openapi: 3.1.0 info: title: Google Omni video API version: 1.0.0 servers: - url: https://gengen.farm/v1 security: - bearerAuth: [] paths: /contents/generations/tasks: post: summary: Create a Omni video task description: > Create an asynchronous video task. Save the returned id and use the [shared task query endpoint](/api-reference/google/omni-retrieve-task) to check status and retrieve outputs.videos. Each POST creates a new task. operationId: createOmniVideoTask requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/OmniRequest' example: model: gemini-omni-1.1-flash-preview mode: text_to_video prompt: A cinematic ocean sunrise with gentle surf sounds. controls: duration: 4 resolution: 720p ratio: '16:9' generateAudio: true outputCount: 1 responses: '200': description: Owned asynchronous video task content: application/json: schema: $ref: '#/components/schemas/OmniTask' example: id: omni:12345678-1234-4234-8234-123456789abc model: gemini-omni-1.1-flash-preview status: queued outputs: videos: [] images: [] createdAt: '2026-10-09T09:58:00.000Z' updatedAt: '2026-10-09T09:58:00.000Z' '400': description: Invalid or unsupported request '402': description: Insufficient balance '503': description: Video generation is temporarily unavailable components: schemas: OmniRequest: type: object required: - model - prompt properties: model: type: string enum: - gemini-omni-1.1-flash-preview - gemini-omni-flash-preview mode: type: string enum: - text_to_video - image_first_frame - image_first_last_frame - multimodal_reference - video_extend - video_modify description: >- Inferred from assets when omitted; sourceVideo defaults to video_modify. Omni Flash supports text_to_video and video_modify; all modes are supported by Omni 1.1 Flash. prompt: type: string minLength: 1 maxLength: 10000 assets: type: object additionalProperties: false properties: firstFrameImage: type: string pattern: ^(https://|gs://) description: >- HTTPS URL or account-authorized gs:// object URI. External private GCS objects require read access configured with GENGEN support. lastFrameImage: type: string pattern: ^(https://|gs://) description: >- HTTPS URL or account-authorized gs:// object URI. External private GCS objects require read access configured with GENGEN support. referenceImages: type: array minItems: 1 maxItems: 10 items: type: string pattern: ^(https://|gs://) description: >- HTTPS URL or account-authorized gs:// object URI. External private GCS objects require read access configured with GENGEN support. sourceVideo: type: string pattern: ^(https://|gs://) description: >- HTTPS URL or account-authorized gs:// object URI. External private GCS objects require read access configured with GENGEN support. referenceVideos: type: array minItems: 1 maxItems: 3 items: type: string pattern: ^(https://|gs://) description: >- HTTPS URL or account-authorized gs:// object URI. External private GCS objects require read access configured with GENGEN support. description: >- Choose frames, reference images/videos, or one sourceVideo for editing/extension. Do not mix these input forms. Images: 20 MiB; MP4 videos: 64 MiB and at most 10 seconds each. controls: type: object additionalProperties: false properties: duration: type: integer minimum: 3 maximum: 10 default: 5 description: >- Requested video duration in seconds. Final charges use returned token usage. resolution: type: string enum: - 360p - 720p - 1080p - 4k default: 720p description: >- Omni Flash supports 720p only; Omni 1.1 Flash supports all listed resolutions. ratio: type: string enum: - '16:9' - '9:16' default: '16:9' generateAudio: type: boolean default: true const: true outputCount: type: integer minimum: 1 maximum: 1 default: 1 providerOptions: type: object additionalProperties: false properties: google: type: object additionalProperties: false properties: {} OmniTask: type: object required: - id - model - status - outputs properties: id: type: string example: omni:12345678-1234-4234-8234-123456789abc model: type: string enum: - gemini-omni-1.1-flash-preview - gemini-omni-flash-preview status: type: string enum: - queued - running - succeeded - failed outputs: type: object required: - videos - images properties: videos: type: array items: type: string format: uri description: >- Temporary HTTPS links; empty for unfinished, failed or expired media. images: type: array maxItems: 0 items: type: string expiresAt: type: string format: date-time description: Video retention deadline; seven days after completion. urlsExpireAt: type: string format: date-time description: >- Signed links expire within one hour. Retrieve again to renew before media expiry. createdAt: type: string format: date-time updatedAt: type: string format: date-time failureReason: type: string securitySchemes: bearerAuth: type: http scheme: bearer ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.