FLUX 3 Video opens to everyone: 20-second clips that arrive with their own sound
Black Forest Labs made FLUX 3 Video generally available through its API on Tuesday, following July's limited release of the multimodal FLUX 3 model. It generates clips up to 20 seconds at 720p or 1080p with the audio created in the same pass — dialogue, sound effects and ambience, no lip-sync post-processing — and speaks more than a dozen languages, including English, Chinese, Spanish, Hindi and Turkish. It also handles image-to-video, keyframe editing, video continuation and multi-shot sequences.
Why it mattersSound has been the missing half of AI video — most rivals bolt it on after the fact. Generating picture and audio together, and shipping it as an open API rather than a closed app, puts a Sora-class tool in developers' hands from a European lab best known for open-weight image models.
▶ Related video: FLUX 3 Might Be the Open Source Sora 2 We Deserve
Read in the app — free, in 9 languages
Related stories
Apple Music will tell you when a song was made by a machine — but the uploader decides whether to say so2026-08-21DeepSeek's cheap workhorse can now see — and on agent tasks that need eyes it says it is close to Anthropic's best
2026-08-21Adobe will now generate the music, the voiceover and the door slam — and it says the licence covers you
2026-08-21Show the robot once — three to twelve seconds — and it gets the job right 59 times out of 100 with no training at all
2026-08-21Six months ago Hollywood sent ByteDance a cease-and-desist. This week they signed a truce — and no money changed hands.
2026-08-20