Scenario
← All Models
Video

Ovi I2V

Use it ↗

Ovi I2V by Character AI generates 5-second videos with perfectly synchronized audio and lip-sync from image inputs. Pricing from 30 credits.

Ovi I2V (Image-to-Video + Audio) transforms a static image—together with a descriptive prompt—into a dynamic video sequence complete with synchronized speech and sound design. It animates the subject, lip-syncs to provided dialogue, and embeds ambient audio or effects to match the scene. Using the same architecture as Ovi T2V, Ovi I2V ensures coherence between visuals and audio, bringing still portraits to life as fully expressive audiovisual scenes.

More models from Character AI