Live4 endpoints

Gemini Omni 1.2 Flash API — Text, Image, Reference & Video Edit

Gemini Omni 1.2 Flash brings Google's native multimodal video model to four focused endpoints: text-to-video, image-to-video with optional last frame, reference-to-video with up to six images, and text-instruction video editing.Clips run 3–15 seconds from 360p drafts up to 4K with natively synchronized audio, priced per second at rates below Gemini Omni 1.1 Flash, using the same asynchronous submit-and-poll contract.

Get a Gemini Omni API Key Try Text to Video Try Video Edit

Gemini Omni 1.2 Flash is available now via API

Try text-to-video or video edit in the playground. Gemini Omni 1.1 Flash and the original Gemini Omni endpoints remain available too.

Gemini Omni 1.2 Flash

3–15s clips, 360p to 4K, native audio, and per-second pricing4 endpoints

T2VLive

Flash

Gemini Omni 1.2 Flash Text to Video

Generate 3–15 second clips from a text prompt with native synchronized audio, 16:9, 9:16 or auto aspect ratio, and 360p to 4K output.

360p–4K

From $0.023/sec

Try Model

I2VLive

Flash

Gemini Omni 1.2 Flash Image to Video

Animate a starting image into video, with an optional last frame for a controlled first-to-last-frame transition.

360p–4K

From $0.023/sec

Try Model

R2VLive

Flash

Gemini Omni 1.2 Flash Reference to Video

Guide subject, scene, or style with one to six reference images while the model composes new motion and audio.

360p–4K

From $0.023/sec

Try Model

V2VLive

Flash

Gemini Omni 1.2 Flash Video Edit

Apply a text instruction, with optional reference images, to restyle or transform a source video up to 15 seconds.

360p–4K

From $0.048/sec

Try Model

What is Gemini Omni 1.2 Flash?

Gemini Omni 1.2 Flash is the latest Flash release in Google's native multimodal video family. Rather than generating silent video and adding sound later, it produces dialogue, ambient sound, and music in the same pass as the picture.

Muapi wraps it as four focused endpoints: text-to-video, image-to-video, reference-to-video and video edit. Every endpoint renders from 360p to 4K and bills per second of output.

What's in 1.2 Flash

Four focused endpoints

Pick text, first/last-frame, reference-image, or video-edit mode without juggling optional fields on one request.

3–15 second clips

Generate clips up to 15 seconds long; first-and-last-frame transitions run 3–10 seconds.

360p drafts to 4K delivery

Validate prompts cheaply at 360p, then re-render the winner at 720p, 1080p, or 4K.

Native synchronized audio

Dialogue, ambient sound, and music are generated together with the video in a single pass.

Per-second pricing

Pay $0.023, $0.07, $0.105, or $0.21 per second at 360p, 720p, 1080p, and 4K, with no subscription.

Gemini Omni 1.2 Flash use cases

Social video at scale

Generate 9:16 clips with built-in sound for Reels, Shorts, and TikTok.

Character and product consistency

Feed up to six reference images to keep a subject consistent across new scenes.

Keyframed transitions

Anchor a first and last frame and let the model generate the connecting motion.

Restyling existing footage

Turn live-action clips into anime, claymation, or new looks with one instruction.

Low-cost draft workflows

Iterate at 360p, then upscale the approved concept to 1080p or 4K.

Gemini Omni 1.2 Flash vs Gemini Omni 1.1 Flash

Feature	Gemini Omni 1.2 Flash	Gemini Omni 1.1 Flash
Clip length	3–15 seconds	4, 6, 8, or 10 seconds
720p price	$0.07 per second	$0.10 per second
Resolution options	360p, 720p, 1080p, 4K	720p, 1080p, 4K (360p on edit)
Aspect ratio	16:9, 9:16, auto	16:9, 9:16
Endpoint shape	Four endpoints: text, image, reference, edit	Text, image, reference, and edit endpoints
Status	Available now on Muapi	Available now on Muapi

Quick start — Gemini Omni 1.2 Flash API

Choose a text, image, or edit endpoint, submit JSON with your Muapi API key, and poll the returned request ID.

Submit a text-to-video task

curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-2-text-to-video \
  -H "x-api-key: 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"}'

# Response: {"request_id":"REQUEST_ID"}

Use text-to-video with a prompt, duration from 3 to 15 seconds, aspect ratio, and resolution.

Animate an image

curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-2-image-to-video \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A smooth transition from dawn to a bright afternoon","first_frame_url":"https://example.com/first.jpg","last_frame_url":"https://example.com/last.jpg","duration":8,"resolution":"1080p"}'

# Response: {"request_id":"REQUEST_ID"}

Use image-to-video with first_frame_url and an optional last_frame_url for controlled transitions.

Edit an existing video

curl -X POST https://api.muapi.ai/api/v1/gemini-omni-flash-1-2-video-edit \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Make this video anime. Keep everything else the same.","video_url":"https://example.com/clip.mp4","resolution":"720p"}'

# Response: {"request_id":"REQUEST_ID"}
# Reference-to-video: POST /gemini-omni-flash-1-2-reference-to-video with prompt + image_urls (1-6).

Use video edit with a source video_url and a text instruction; output length follows the source.

Retrieve the completed result

curl https://api.muapi.ai/api/v1/predictions/REQUEST_ID/result \
  -H "x-api-key: YOUR_API_KEY"

# Poll until status is completed, then read the generated video URL.

Poll the standard prediction result endpoint and read the generated video and audio outputs.

Gemini Omni 1.2 Flash FAQ

What is Gemini Omni 1.2 Flash?

It is Google's latest Flash release in the Gemini Omni multimodal video family, available through four Muapi endpoints: text-to-video, image-to-video, reference-to-video, and video edit.

How is Gemini Omni 1.2 Flash priced?

Generation is billed per second of output at $0.023 (360p), $0.07 (720p), $0.105 (1080p), and $0.21 (4K). Video edit adds $0.02 per second of source video to the output rate.

How long can clips be?

Text, image, and reference endpoints generate 3 to 15 seconds; first-and-last-frame transitions are limited to 3 to 10 seconds. Video edit accepts source clips up to 15 seconds.

Can I combine a starting frame with reference images?

No. Image-to-video takes a first frame and optional last frame, while reference-to-video takes one to six reference images. Use the endpoint that matches your input mode.

Does it generate audio?

Yes. Dialogue, ambient sound, and music are generated natively with the video, so no separate audio step is needed.

Is Gemini Omni 1.2 Flash available on Muapi now?

Yes. Try any endpoint in the playground or call it from the API with a Muapi key. Gemini Omni 1.1 Flash and the original endpoints stay available.

Explore Gemini Omni →See the full multimodal family, including voices and characters.Gemini Omni 1.1 Flash →Compare with the previous Flash release and its endpoints.Browse video models →Compare 1.2 Flash with other live video generation APIs.Create an API key →Start using Gemini Omni 1.2 Flash through Muapi.

Ready to use Gemini Omni 1.2 Flash?

Generate 3–15 second clips with native audio from 360p to 4K, all through one API.

Get an API Key Try Reference to Video