Audio-driven talking or singing avatar generation from a single image with lip-synced motion and consistent identity. Supports 480p/720p output up to 2 minutes.
Added Dec 24, 2025
Approx. Price
$0.150 per video
Model Type
image-to-video
Preview Examples
5
Generation controls available for this model.
Resolution/Aspect Options
2
Default Duration
N/A
Tunable Settings
2
Prompt
Default
N/A
Optional expression/style prompt
Resolution
Default
480p
Options (2)
480p, 720p
Video resolution
Human preference benchmarks sourced from Artificial Analysis.
No Artificial Analysis benchmark data is available yet for this model.
Artificial Analysis APIAudio-driven talking avatar with accurate lip synchronization and natural head motion.
Realistic lip-synced avatar preserving identity and expression across frames.
Full-body coherent avatar with synchronized facial expressions and posture.
Natural dynamics avatar with consistent identity and smooth motion.
High-quality talking avatar with precise lip sync and expressive movement.
