May – Jun 2025
Sound in the same pass
Veo 3, Flow and the recipe behind the Veo 3 ad.
Video models learned to speak. Veo 3 generated dialogue, sound effects and ambience in the same pass as the picture, which made short spoken scenes and ads possible in a day. Around it appeared the first director apps for arranging shots into a sequence.
Tutorials2
Veo 3 talking-animal vlogs, explained
Community tutorial · YouTube · 2025
How it worked
- Write the script, then have an LLM draft a prompt per shot with the dialogue in quotes.
- Generate each shot in Veo 3 (eight seconds, native dialogue, effects and ambience), text-to-video or from a still.
- Assemble and extend in Flow's Scenebuilder with camera controls and asset management, or cut in Premiere.
- Seedance 1.0 introduced native multi-shot: two or three cuts inside a ten-second clip.
- For the rest of the stack: Midjourney Video animates any Midjourney image; Higgsfield Soul locks a character; Eleven v3 adds inline audio tags and multi-speaker dialogue.
Behind the scenes2
How films were actually made, from the people who made them.
Related on the timeline4