Overview
Google's fast, conversational video generation and editing model — ideal for iterative creative workflows needing natural-language video edits rather than one-shot generation.
Key Features
- Fast, cost-efficient model for video generation and conversational editing, released June 30, 2026.
- Multi-input reasoning supporting text, images, audio, and video inputs simultaneously.
- Multi-turn conversational editing for element replacement or perspective changes.
- Generates 3-10 second clips at 720p and 24fps in 16:9 or 9:16.
- Priced at $0.10 per second of video output, matching Veo 3.1 Fast pricing.
Input Capabilities
Text
Image
Advanced Options
Technical Specifications
Model Information
Provider: Google
Model Code: gemini-omni-flash-preview
Category: Video Generation
File Support
Max Files
1
Max Size
10MB
Supported Formats
.jpg
.png
.jpeg
.webp
Other Google Models
Veo 3.1Premium flagship model with cutting-edge video generation capabilities - ideal for cinematic productions, storytelling, and professional content with frame control and reference image support
Veo 3.1 FastFast variant of Veo 3.1 optimized for speed and cost - perfect for business applications, advertising content, and high-volume video generation requirements
Veo 3.0Premium flagship model with revolutionary native audio generation - ideal for cinematic productions, storytelling, and professional content requiring synchronized audiovisual experiences