Veo 3 Adds Speech Generation to Frames to Video, Expands AI Tool to 76 More Countries

Starting this week, users can add speech to their video clips in Flow, the AI tool for filmmakers, when using the Frames to Video feature. This enhancement allows you to bring your own images to serve as the starting frame of a video clip, complementing the existing capabilities of Veo 3 to add sound effects and background noise. Now, with the addition of speech generation, creators can produce more dynamic and engaging content. Since its launch in May, tens of millions of videos have been generated using Flow, showcasing its growing popularity and utility. To maximize the value for users, Frames to Video is being introduced on Veo 3 Fast, enabling more efficient credit usage. It’s important to note that the audio generation feature is still in the experimental stage, and the quality of the generated speech may vary as improvements continue. In an effort to make Flow and Google AI Ultra — which provides the highest level of access to advanced Google AI tools — available to a wider audience, the platform is expanding to 76 additional countries. This expansion brings the total number of countries where Flow is accessible to over 140, provided users have a Google AI Pro or Ultra plan. For detailed country availability, please refer to the official announcement. However, the availability of certain product features may differ based on the country of use, and some image types might not be supported. Despite these limitations, the expansion aims to empower more creators around the globe to leverage the powerful tools offered by Flow and Google AI Ultra in their projects.