Skip to main content
A presenter clip from a script you supply.
1

Voice the script

generate_audio (a TTS model, your script, a voiceId). Capture the audio output id.
2

Lip-sync

generate_lip_sync (a portrait image plus the audio output id) for the talking-head video.
3

Assemble and publish

create_card, then one update_card carrying the video in assets, the platform in posts, and scheduledAt.
The script is yours. If you have not written one, that is a grounded pipeline Draft, not an invention: your agent grounds it in your voice and you approve it first.