Pick a format the channel can keep
Most faceless channels run on one of two formats. A presenter channel has the same character talk to camera in every video: one photo, lip synced to each new voiceover, so the face stays consistent from upload to upload. A narrated channel has no presenter: the voiceover runs over scenes and images, made with the AI video generator or animated from still images.
One voice across every video
A channel is recognised by its voice. Pick one of the AI voices and keep it, or clone your own once from a short clean sample if you want your voice without your face. Every voice model and its price is on the AI voice generator page. Already recorded the audio? Turn it into a talking video as it is.
What it costs
The talking presenter is priced per second of video: 2 credits a second on the fast lip sync model at 480p, so a 60 second clip is 120 credits, or 6 credits a second at 720p on the higher quality model. Voiceovers start at 2 credits a clip and images at 1 credit. The playground quotes the exact cost before anything runs, and a run that fails is refunded.
Percify makes the videos; you download them and upload them yourself. To post and schedule across platforms, see Percify Brand OS on percify.ai.