Mini toolsp video avatar
By Pruna AI
p-video-avatar is a production avatar-video model in Pruna’s API, built for turning one portrait image into a speech-driven talking-head video. The docs say it accepts an input image plus either voice_script or audio, with audio taking priority when both are provided, and supports selectable voices, output language, optional video and voice prompts, reproducible seeds, and 720p or 1080p rendering. Pruna lists it under Video Generation with pricing at $0.025 per second for 720p and $0.045 per second for 1080p, positioning it for realistic avatar delivery rather than general video generation.
New
Multimodal
Overview
p-video-avatar is Pruna’s talking-head video generation model for creating speaking avatar videos from a single portrait image. It takes either a text script or an audio file, then generates a realistic head-and-shoulders speaking video, with support for multiple voices, languages, and 720p or 1080p output.
About Pruna AI
Pruna is your trusted partner in leveraging the best AI has to offer for your business goals.
Website:
pruna.ai
Last updated: July 7, 2026
