Kandinsky 6.0 Video ships open weights with 44 kHz audio
Kandinsky Lab released Lite (3B) and Pro (29B) free under MIT, with five-second clips and lip-sync that run on a 16 GB GPU.
Everything we've published, newest first.
Kandinsky Lab released Lite (3B) and Pro (29B) free under MIT, with five-second clips and lip-sync that run on a 16 GB GPU.
CBS had Runway build the synthetic studio intro, which the show says took about five minutes, then told viewers no more AI content is coming.
Griffin is the first system to pass a video Turing test, and the company that built it says it is not safe to sell yet. Based Boomerstein has not stopped pacing since.
Asuka Publishing's AI Douga Saizensen carries 12 interviews and copyright guidance from a lawyer whose firm the publisher says sits on the justice ministry's AI legislation committee.
U.S. District Judge Jacqueline Scott Corley denied ByteDance's motion to dismiss on October 2, holding the creators plausibly alleged a lost-advertising injury tied to circumvention.
The beta runs on web, iOS and Android, tops out near eight minutes, and lets creators switch the music off for plain narration.
Google's open model unifies text, images, audio and video in one vector space, so a voice memo can find the matching shot without leaving the phone.
Members vote until October 29 on a four-year contract that would require a studio to get a voice actor's consent before dubbing a performance with a cloned voice.
Advantage+ Creative can now turn still images into video ads and catalog advertisers can generate product video at scale, and Meta says video is more than 60% of Facebook and Instagram time.
The AI video company's new product lets people hold live conversations with lifelike avatars, starting with sales roleplay practice and interview-style surveys.
Real actors filmed on a gray screen for one day, AI environments built around them, and a finished trailer in under three weeks.
The signed metadata that marks a video as AI-generated survives to the audience roughly a third of the time, and the EU now puts the disclosure duty on whoever publishes.
The two open-weight models return a probability instead of a sentence, accept images and video, and are free to download under Apache 2.0.
The platform from filmmaker Dan Hartley and former Prime Video UK boss Chris Bird turns a script into photo-realistic images and video, then carries the project through budgeting and scheduling.
MAI-Transcribe-2-Streaming returns partial text in about 100 milliseconds, and two new voice models join it for real-time agents.
HeyGen Video is a fine-tune of MiniMax's H3 model and generates 5 to 15 second clips with their own audio, at half its regular price through October.
The 2026 Small World in Motion winner says AI only colored the footage after imaging; critics point to a SynthID watermark on the clip.
A $300 million employee share sale led by Wellington and T Rowe Price values the voice AI company at twice its February round.
The browser game, built with Claude Opus 5.5, drew 3.5 million views before ZeniMax sent a cease-and-desist over the Fallout name.
The Arizona Court of Appeals upheld the manslaughter conviction but ordered a new sentencing hearing, saying the AI depiction of the victim prejudiced the trial judge.