Stay up-to-date with changes in Flow

Find the latest fixes, improvements, and feature announcements to Flow below.

Updates

Flow Nov 11, 2025 update

Introducing a better way to create and edit images in Flow!

Select “Create Image” from the prompt box to start generating images within a specific project. You can select between our Nano Banana and Imagen4 models for generating images in the prompt box. Generated images will live in the “Image” tab within a specific project, and can be edited on hover using Nano Banana.

Images (and all iterative edits) can also be added to the ingredients drawer and used as ingredients or frames when creating other images or videos. Simply use the “Add to Prompt” button on hover of images to add it to your prompt box and ingredients drawer.

Flow July 7, 2025 update

Thank you for being a Flow user and for your continued feedback! We have plenty of new features to give you more speech and more generations.

You can now make your images talk with Veo 3

Veo 3 first-frame to video now supports speech. Upload a picture of your character and give them a voice. Note that audio is still a beta feature, so your videos might not always return sound.

Reminder: By using this feature, you confirm that you have the necessary rights to any content that you upload. Do not generate content that infringes on others’ intellectual property or privacy rights.

We’re adding a Veo 3 Fast option for Frames to Video

You loved Veo 3 - Fast Text to Video, so we’re excited to extend this option to Frames to Video as well. In both modes you can now select this faster and cheaper option to get more out of your credits.

Pro subscribers can now top-up

You told us the gap between Pro and Ultra was too steep: we heard you. If you’ve run out of AI Credits before your monthly refresh, you can now simply navigate to your profile page in the top right corner and click “Add AI Credits” to purchase top-ups.

Other improvements

Increased audio coverage when using Veo 3
Reduction in unwanted subtitles when using Veo 3
Various bugs and latency issues (more to come)

Thank you and keep feedback coming,

The Flow Team.

Flow June 9, 2025 update

Here’s a few things we’ve fixed and updated, and some best practices to get the most out of the tool. Please continue to leave us feedback anytime in the three dot menu!

Veo 3

The excitement for our latest model, Veo 3, has been overwhelming! We’re excited to bring in a new Veo 3 - Fastoption for text to video that only costs 20 credits (1/5th of Veo 3-Quality).

Please remember that:

Veo 3 - Qualityoffers text-to-video and first-frame to Video.
Veo 3 - Fastoffers text-to-video.
We’re working on bringing extend, first + last frame, ingredients to video and more to Veo 3 soon.
If you select one of these Veo 2 features we’ll suggest switching to the corresponding model.

Based on feedback we’ve also updated naming for legibility and consistency. “Veo 3 - Highest Quality” is now “Veo 3 - Quality”; “Experimental Audio” is now “Beta Audio”. They are the same underlying models.

Audio availability

Audio is still an experimental feature , and available on Veo 3 only. We’re working on improving coverage but note that your generated videos might not always have sound. Things to know

Speech does better with slightly longer transcripts.
Speech is muted on minors.
Speech can trigger subtitles (we’re working on it).

Bugs & Improvements

Thumbnails: fixed issues around previewing videos and missing thumbnails.
Scenebuilder: sound support for Veo 3 clips, Veo 3 jump to, fixed some multi-clip behavior.
Upscaling: upscale to 1080p at no charge, fixed sound on Veo 3 upscales.
Downloading: Fixed reliability of downloading outputs from scene builder.
Image uploads: now supports WebP and HEIC file formats, reduced rejections.

Other

Flow access has expanded to 70+ countries.
Veo 3 was made available in Pro tier.