AI Intelligence
Google launches Gemini Omni Flash, a conversational video-generation model with avatar mode held back
Source: The Next Web AI · Category: AI Products & Releases Google launched Gemini Omni Flash, a multimodal video-generation model accepting image, audio, video, and text inputs, with speech-editing withheld and SynthID watermarking enabled by default. This advances Google's competitive position in video AI alongside text and multimodal capabilities.