Generate video from text with Gemini Omni 1.2 Flash. 3-15 second clips with native audio at 360p to 4K, pay per second. Try free. Gemini Omni 1.2 Flash — text-to-video generation with native synchronized audio, 3-15 second clips from 360p to 4K.
Gemini Omni 1.2 Flash — text-to-video generation with native synchronized audio, 3-15 second clips from 360p to 4K.
About this model
Gemini Omni 1.2 Flash is Google's fast multimodal video model, and this is its text-to-video endpoint: write a prompt describing the scene, action, camera, and sound, and receive a 3-15 second clip with natively synchronized dialogue, ambient audio, and music generated in the same pass. Choose 16:9, 9:16, or auto aspect ratio and render at 360p for cheap drafts or up to 4K for final delivery. Pricing is per second of output ($0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K), so cost scales predictably with clip length. To start from an image instead, use Gemini Omni 1.2 Flash Image to Video; to condition on reference images see Gemini Omni 1.2 Flash Reference to Video; to edit an existing clip see Gemini Omni 1.2 Flash Video Edit.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapi | $0.023–$0.21 per second (by resolution) | Pay-per-generation, no subscription. Billed per second of generated video. |
| Fal.ai | Not available | This model is not listed on Fal.ai. |
| Replicate | Not available | This model is not listed on Replicate. |
Pay-per-generation, no subscription. Billed per second of generated video.
This model is not listed on Fal.ai.
This model is not listed on Replicate.
** Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Describe the scene, action, camera movement, and sound. | A cat plays piano in a jazz bar, one continuous shot, soft live jazz |
| Duration | integer | Video length in seconds (3-15). | 8 |
| Aspect Ratio | Enum (3 options) | Output aspect ratio. `auto` follows the reference image and is treated as 16:9 when none is provided. | 16:9 |
| Resolution | Enum (4 options) | Output resolution. Output priced per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K. | 720p |
| Seed | integer | Random seed (10000-99999). Omit for a random seed. | - |
Describe the scene, action, camera movement, and sound.
A cat plays piano in a jazz bar, one continuous shot, soft live jazzVideo length in seconds (3-15).
8Output aspect ratio. `auto` follows the reference image and is treated as 16:9 when none is provided.
16:9Output resolution. Output priced per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K.
720pRandom seed (10000-99999). Omit for a random seed.
-Developer documentation
Write a multimodal prompt Describe visuals, camera direction, dialogue, and ambient sound together. Example: 'A cat plays piano in a jazz bar, one continuous shot, soft live jazz.'
Pick duration, aspect ratio, and resolution
Duration is 3-15 seconds. Aspect ratio is 16:9, 9:16, or auto (treated as 16:9 without a reference image). Resolution is 360p, 720p, 1080p, or 4k. Billing is $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K.
Optionally set a seed
Pass seed (10000-99999) to make renders reproducible.
Submit and poll
curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-2-text-to-video
-H "Authorization: Bearer YOUR_API_KEY"
-H "Content-Type: application/json"
-d '{"prompt": "A cat plays piano in a jazz bar, one continuous shot, soft live jazz", "duration": 8, "resolution": "720p", "aspect_ratio": "16:9"}'
Then poll `GET /api/v1/predictions/{request_id}/result` until `status` is `completed`.
5. **Prompt tips**
- Describe sound explicitly: *'soft piano underscore'*, *'wind through trees'*.
- Quote dialogue and describe the speaker.
- Name camera moves such as *'slow dolly in'* or *'handheld tracking shot'*.
Frequently asked
It's Google's fast multimodal video model. This endpoint turns a text prompt into a 3-15 second video with natively synchronized audio.
Per second of generated video: $0.023/s at 360p, $0.07/s at 720p, $0.105/s at 1080p, $0.21/s at 4K. An 8-second 720p clip costs $0.56.
Durations of 3-15 seconds and resolutions of 360p, 720p, 1080p, and 4K.
Yes. Dialogue, ambient sound, and music are generated natively in the same pass; describe the sound in your prompt to steer it.
Not on this endpoint. Use [Gemini Omni 1.2 Flash Image to Video](/playground/gemini-omni-flash-1-2-image-to-video) for a starting frame or [Gemini Omni 1.2 Flash Reference to Video](/playground/gemini-omni-flash-1-2-reference-to-video) for reference images.
Send the same `seed` (10000-99999) with the same prompt and settings.