YouTube lays out new rules for 'realistic' AI-generated videos
'Clearly unrealistic' content won't need to include a disclosure.
Many companies and platforms are wrangling with how to handle AI-generated content as it becomes more prevalent. One key concern for many is the labeling of such material to make it clear that an AI model whipped up a photo, video or piece of audio. To that end, YouTube has laid out its new rules for labeling videos made with artificial intelligence.
Starting today, the platform will require anyone uploading a realistic-looking video that "is made with altered or synthetic media, including generative AI" to label it for the sake of transparency. YouTube defines realistic content as anything that a viewer could "easily mistake" for an actual person, event or place.
If a creator uses a synthetic version of a real person's voice to narrate a video or replaces someone's face with another person's, they'll need to include a label. They'll also need to include the disclosure if they alter footage of a real event or place (such as by modifying an existing cityscape or making it look like a real building is on fire).
YouTube says that it might apply one of these labels to a video if a creator hasn't done so, "especially if the altered or synthetic content has the potential to confuse or mislead people." The team notes that while it wants to give creators some time to get used to the new rules, YouTube will likely penalize those who persistently flout the policy by not including a label when they should be.
These labels will start to appear across YouTube in the coming weeks, starting with the mobile app and then desktop and TVs. They'll mostly appear in the expanded description, noting that the video includes "altered or synthetic content," adding that "sound or visuals were significantly edited or digitally generated."
However, when it comes to more sensitive topics (such as news, elections, finance and health), YouTube will place a label directly on the video player to make it more prominent.
Creators won't need to include the label if they only used generative AI to help with things like script creation, coming up with ideas for videos or to automatically generate captions. Labels won't be necessary for "clearly unrealistic content" or if changes are inconsequential. Adjusting colors or using special effects like adding background blur alone won't require creators to use the altered content label. Nor will applying lighting filters, beauty filters or other enhancements.
In addition, YouTube says it's still working on a revamped takedown request process for synthetic or altered content that depicts a real, identifiable person's face or voice. It plans to share more details about that updated procedure soon.
