Model Library

Lip Sync & Talking Video Models

Choose the best model for dubbing, avatar videos, or text‑driven generation.

models.categories.videoToVideo.label

models.categories.videoToVideo.blurb

Balanced quality and speed for general lip‑sync dubbing.

Higher facial detail and realism for close‑ups.

Emotion‑aware sync with subtle facial expression control.

Legacy, lightweight option for fast processing.

Diffusion‑based sync with strong temporal consistency.

Reliable video lip sync with fast turnaround.

Clean, straightforward lip sync for standard formats.

models.categories.audioToVideo.blurb

Stable talking heads for longer content and multi‑speaker scenes.

Consistent identity for single‑speaker narration.

Turn a single photo and audio into a lip‑synced digital human video.

Audio‑driven lip sync with high precision.

models.categories.textToVideo.blurb

Generate lip‑synced video directly from a script.

models.categories.dubbing.blurb

Localized output with synced lip movement.

Dub videos with language detection and voice selection.

models.categories.new.blurb

New multi‑shot video model with strong consistency.