The image reference sets the speaker's face and wardrobe; the audio reference sets her voice. She sits at a kitchen table, glances at the camera and starts talking, one hand around a mug. Locked medium shot, morning light.
Same model, starting from this prompt. Other settings use their defaults.
Why this prompt works
`reference_audio_urls` supplies the voice and `reference_image_urls` supplies the face and wardrobe — separate references, since a clip with the wrong voice behind a familiar face reads as wrong even when the picture is right. The prompt adds only blocking: kitchen table, a hand around a mug, a glance up before she speaks. `duration_seconds` `10`, `resolution` `720p`.
Settings used
Setting
Value
What it does
resolution
720p
480p, 720p or 1080p. Defaults to 720p. Resolution changes both the price and how long the task takes to come back.
duration_seconds
10
Any whole number from 2 to 30, or -1 for smart duration. Defaults to 5. With reference videos, their total length plus this value must stay within 30 seconds, and those seconds are billed on top of the output. Settle the look at 5 seconds before extending.
Preview blurred