FLUX.3 Text to Video by Black Forest Labs generates video and matching audio together from a single prompt, so speech, sound effects and score are created in sync with the action. Write a detailed, cinematic prompt covering subject, motion, camera, style and the audio you want, then pick a duration from 5 to 20 seconds at 720p or 1080p in aspect ratios from 21:9 to 9:16. It follows complex multi-beat prompts with natural motion and multilingual dialogue. Ideal for trailers, ads, game cinematics, previz and social content.