Google Labs

Google's new AI tool, Whisk, allows you to generate images by using other images as prompts. Simply drag in images for the subject, scene, and style, and remix them to create unique, personalized visuals without needing long text prompts.

Speech in Flow is a new experimental feature for Google's AI filmmaking tool, Flow. Powered by Veo 3, it lets you add custom, AI-generated speech to videos created from a single starting image, bringing your pictures to life with dialogue.
Co-hunting with @busmark_w_nika to share this fun yet powerful update to Flow.

I just tried it out. I uploaded a photo of a hamster and prompted it to pull out an iPhone 16 Pro and say, "hey, I can talk to you now!" The video Flow generated was genuinely astonishing – actually, it gave me two options to choose from.

This is a new aha moment. When an AI can imagine and synchronize both sound and visuals in a single step, it replaces the long, multi-app workflows creators used to struggle with. That's a huge leap.