started · updated
Google launches Gemini Omni 1. 1 Flash for professional video generation
Google has introduced several significant updates to its Gemini AI ecosystem, most notably the release of Gemini Omni 1. 1 Flash, a generative video model designed for professional-grade content creation. This new model features a scene extension capability that allows users to extend existing clips in 10-second increments up to a total of 40 seconds. To maintain visual and narrative consistency, the model analyzes up to 10 seconds of previous footage rather than just the final frame. Additionally, creators can specify both a starting and ending frame, allowing the AI to interpolate the movement between them, which is useful for camera pans, zooms, and seamless loops.
To optimize workflows, Gemini Omni 1. 1 Flash includes a 360p draft mode that renders up to 60% faster and at one-third the cost of standard 720p output, with final results capable of up to 4K upscaling. The model also supports up to three seconds of video references to maintain character and environmental consistency.
In parallel, Google launched Gemini 3. 5 Transcribe, a speech-to-text model that aims to replace traditional dictation tools. It can automatically remove filler words like 'um' and 'uh' and handle self-corrections to produce polished text. The model supports over 85 languages and can distinguish between up to three different speakers. Furthermore, updates to Gemini Live introduce enhanced voice capabilities, integrating the Spark AI agent to handle multi-step tasks in the background and providing spoken summaries of tasks from Gmail and Google Calendar via the Daily Brief feature.
Entities
Gemini · Gemini 3. 5 Transcribe · Gemini 3.5 Transcribe · Gemini Live · Gemini Omni 1. 1 Flash · Gemini Omni 1.1 Flash · Google · Google AI Studio · Spark · Sundar Pichai
Claims
What the coverage asserts, and how many sources carry each claim.
- [● 2 SOURCES] The model allows creators to provide both a starting and ending frame to generate the connecting footage. dailyguardian.ae · www.digitaltrends.com
- [● 2 SOURCES] Developers can generate 360p previews that are reportedly 60% faster than 720p output. dailyguardian.ae · www.digitaltrends.com
- [DISPUTED] The model supports up to three seconds of video references for visual context. dailyguardian.ae · www.digitaltrends.com · ameve.eu · dijitaliyidir.com · ictnews.ir · +8 more
- [● 16 SOURCES] Users can extend videos in 10-second increments up to a total length of 40 seconds. dailyguardian.ae · www.digitaltrends.com · ameve.eu · ictnews.ir · www.tokenpost.kr · +11 more
- [● 13 SOURCES] Google has released Gemini Omni 1.1 Flash, a generative video model. dailyguardian.ae · www.digitaltrends.com · ameve.eu · ictnews.ir · www.tokenpost.kr · +8 more
- [DISPUTED] The model can use up to 10 seconds of previous footage for context to maintain scene consistency. dailyguardian.ae · www.digitaltrends.com · ameve.eu · ictnews.ir · www.tokenpost.kr · +11 more
- [● 6 SOURCES] Gemini Live now includes the Spark AI agent to handle multi-step tasks in the background. www.androidsis.com · www.blog-nouvelles-technologies.fr · marketing4ecommerce.cl · www.phonandroid.com · www.thurrott.com · +1 more
- [● 3 SOURCES] Gemini Live allows users to manage Gmail inboxes via voice commands. marketing4ecommerce.cl · www.phonandroid.com · www.thurrott.com
- [● 17 SOURCES] Gemini Omni 1. 1 Flash introduces 4K export capabilities and extended video scene context. www.tuttoandroid.net · stadt-bremerhaven.de · ameve.eu · ictnews.ir · www.tokenpost.kr · +12 more
- [● 5 SOURCES] Gemini 3.5 Transcribe supports more than 85 languages. kulturegeek.fr · www.smartworld.it · lagazetteia.fr · www.business-punk.com · www.phonetoday.it
- [● 3 SOURCES] The Daily Brief feature provides spoken summaries of tasks from Gmail and Google Calendar. www.androidsis.com · www.phonandroid.com · www.thurrott.com
- [○ 1 SOURCE] Gemini has reached one billion monthly active users. android-mt.ouest-france.fr