Gemini Omni 1.2 Flash

Google's video generation and editing model: native 15-second clips, multi-turn editing, $0.07 per second at 720p.

Google · Generative media (image, video, audio, music, voice/avatar generation) · model

Published in Feed

Overview

Gemini Omni 1.2 Flash, announced by Google on November 5, 2026, generates and edits video natively at up to 15 seconds per clip, up from 10 seconds in Gemini Omni 1.1, with duration settable from 3 to 15 seconds in one-second steps. It accepts character, product or style images, motion reference clips of up to three seconds, and audio cues, and can be refined over multiple conversational turns (swapping a product or background, changing lighting or weather, changing aspect ratio) without regenerating from scratch. Google lists it as generally available in the Gemini API, with Google AI Studio for prototyping and the Google Cloud console and API (Provisioned Throughput offered), and says it also appears in Flow, Google Vids, Google Ads and, for Google AI Ultra subscribers, the Gemini app.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Native video generation and editing up to 15 seconds (Omni 1.1: 10 seconds), duration set 3-15 s
  • Reference inputs: character/product/style images, motion clips up to 3 seconds, audio cues
  • Multi-turn conversational editing of an existing clip without full regeneration
  • Draft at 360p or 720p, then upscale to 1080p or 4K
  • Improved dialogue lip-sync and multi-speaker conditioning
  • All outputs carry an imperceptible SynthID watermark

Use cases

  • Short product and brand video ads with consistent packaging, colors and faces
  • Iterative scene direction and editing in Flow
  • 15-second clips inside Google Vids at no extra cost with a Google account or Workspace subscription
  • Programmatic video generation through the Gemini API or Vertex-style Google Cloud access

Pricing

$0.07 per second of 720p video via API, which Google says is 30% below Gemini Omni 1.1; Google Vids clips included with a Google account or Workspace subscription; Gemini app access for Google AI Ultra subscribers.

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
5 Nov 2026
Record updated
8 Nov 2026
Record last checked
8 Nov 2026

Explore the Feed

Other entries filed under generative media (image, video, audio, music, voice/avatar generation); inclusion does not imply equivalent features.

  • Amazon Nova 2.5 Sonic

    Amazon's generally available real-time speech-to-speech model in Bedrock, with a 256K context window and asynchronous tool calling.

  • Grok Voice 3.0

    xAI's speech-to-speech model in the Voice Agent API, priced at $0.08/min and scoring 86.9 on Artificial Analysis' Speech-to-Speech Index.

  • Helix World

    Real-time interactive world model from Noiz AI and HKUST that generates explorable video with spatial stereo audio from one image.

Browse the Feed