gemini-omni logo

Gemini Omni Flash 1.2

New
Use this model

Create 3-15s video with sound from text or an image, at resolutions up to 4K.

InputsTextImage
OutputsVideoAudio
SpeedFast
Price9–422 credits
CostMedium
ReleasedNov 2026
Pricing details
  • Audio always included. 3.13c/s (360p), 9.38c/s (720p), 14.08c/s (1080p), 28.15c/s (4k); 3-15s clips (default 10s).

Test outputs

Compare all models

Gemini Omni Flash 1.2 in practice

What it does and when to use it.

Model summary

Gemini Omni Flash 1.2 is Google’s fast, low-cost video model. It makes 3 to 15 second clips with sound from a text prompt or a starting image, at 360p up to 4K, in 16:9 or 9:16. It follows long, multi-step prompts, and its sound is strong. Put a line of dialogue in quotes and the character says it. For a recurring character, start from a frame that shows them. Glif charges per second, more at 1080p and 4K, which are upscaled.

Capabilities

Text to video
Image to video
Video with audio
Dialogue generation
Camera motion
Cinematic style

Suggested use cases

  • Long, multi-step scenes other video models can’t follow
  • Shots with a set camera move or point of view
  • Talking heads and short scenes with dialogue
  • Animate a photo or a generated still
  • 15-second clips for Reels, Shorts and TikTok
  • B-roll with matching sound

Gemini Omni Flash 1.2 variants

Edit, extend and reference tools built on the same model.

More from the Gemini Omni Flash family

Explore other options from the same family.

All the models in one place

Run Gemini Omni Flash 1.2 and every other model on Glif from one chat. One account, one balance, no API keys to wire up.