Native-audio video
generate picture and sound together with a supported model
Before you start
- A video brief that explains both the picture and intended sound.
How to use this workflow
Step 1
Select a video model with native audio support.
Step 2
Describe speech, ambience, or sound alongside the visual action and check the audio setting.
Step 3
Listen to the complete result and review synchronization, pronunciation, and unwanted sound.
What to check
Native audio availability does not guarantee exact dialogue, music, or lip synchronization.