LinkGoogleAnnouncement
Integrating video and native audio generation directly into a conversational workflow significantly lowers technical barriers for media production, while built-in SynthID watermarking establishes built-in provenance verification.
By replacing Veo with Gemini Omni 1.1 Flash, Google folds its video generation tech directly into the primary Gemini multimodal pipeline. Key capabilities include multi-step conversational editing, native sound output, and scene extension while retaining visual style. The introduction of personal AI avatars targets digital creators, while embedded SynthID markers support compliance with emerging synthetic media provenance standards.
Summary generated by AI (Gemini 3.8 Flash, 27 September 2026). It may contain errors – the original source is authoritative.
Similar in content, found by the AI search.
Article:Google AI for Developers
Google has documented the integration of Gemini Omni Flash (gemini-omni-1.1-flash) into the Gemini API. The multimodal model processes text, image, audio, and video simultaneously, enabling text-to-video and image-to-video generation with integrated sound.
Article:Anish Nangia, Alisa Fortin
Google has announced Gemini Omni 1.1 Flash, bringing enhanced developer controls for generative video production, including scene extensions up to 40 seconds, keyframe interpolation, 360p draft generation, and 4K upscaling.
Link:Google
Google has launched Google Flow, an AI creative studio integrating image and video generation with conversational editing and custom tool creation. Powered by models such as Gemini Omni, Veo 3.1, and Nano Banana, the suite covers the entire pipeline from planning to final refinement.
Article:Tulsee Doshi
Google has launched Gemini 3 Flash, a cost-effective and high-speed model designed to bring Gemini 3 reasoning capabilities to latency-sensitive and high-frequency workflows.
Link:Google DeepMind
Google DeepMind has introduced Gemini 3.8 Flash, an agentic workhorse model designed for complex multi-step reasoning, coding, and knowledge tasks at low latency. The multimodal model supports a 1M token input context alongside extensive tool integration.
Article:Tulsee Doshi
Google has announced Gemini 3.7 Flash, an updated workhorse model focused on software engineering and autonomous agents. Arriving three weeks after version 3.6 Flash, the model delivers measurable benchmark gains alongside a halved introductory token price.
Parts of this content were created with the assistance of AI.
