Product
Spokesperson Videos: Lip-Sync From a Single Photo
3 min read
Spokesperson content is one of the highest-converting formats in paid social, and it used to require an actor, a camera, and a shoot. Now it takes a photo and an audio clip.
Hand the studio a single portrait and a voice track and Hedra Character-3 generates a lip-synced talking-head video, matching mouth movement and expression to the audio. Record your own voiceover, or generate one first and feed it in.
It pairs naturally with the rest of the pipeline: write a script, generate a voice, lip-sync a presenter, then cut it against product shots and b-roll into a finished spot.
Lip-sync runs 14 credits per generation, included in every plan.
Brief once. Get a finished short.
Start creating free