Skip to content
NewA calmer, faster ZeroHour

Google releases Gemini Omni 1.2 Flash with 15-second clips and 30% price cut

Original title: Gemini Omni 1.2 Flash: Fast and cost-effective with longer clips

Google · AIby Anish Nangia ()4 min read1 · 1 read
Part of a story covered by 4 sourcesGoogle Makes Gemini Omni 1.2 Flash Generally AvailableMerged summary & timeline
AI summary · zhipu/glm-5.3-deriskedSummaries by Vani AI

The model adds multi-turn editing, spoof-resistant reference following and SynthID watermarks; general availability is a first for Gemini Omni.

Google made Gemini Omni 1.2 Flash generally available across the Gemini API and Gemini for business. The video model supports native 15-second clips, multi-turn conversational editing, better reference adherence and character consistency, and more natural speech with clearer lip-sync. Google cut the price 30% to $0.07 per second for 720p video and says outputs carry a SynthID watermark.

Key facts
  • 720p generation costs $0.07 per second, 30% below Gemini Omni 1.1.
  • Clips extend to 15 seconds, up from 10, with one-second increments.
  • Outputs carry a SynthID watermark; Provisioned Throughput is available.
  • Known weak areas include fast sports action and complex physics.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

4 min read at blog.google

Gemini Omni 1. 2 Flash brings native 15-second video generation and editing, stronger consistency, and 30% lower pricing.

Google · AI

By Anish Nangia · blog.google

Read the full article at Google · AI

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.