P-Video Avatar — model skill for talking heads & avatars

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

Turn one portrait into a speaking avatar video with Pruna P-Video-Avatar, its built-in TTS or your audio.

What it does

Generates talking-head avatar videos from a portrait with Pruna P-Video-Avatar through inference.sh: text-to-avatar with built-in TTS (30 voices, 10 languages) or audio-driven avatars, at 720p or 1080p. The vendor pitches it as much faster and cheaper than competing avatar models.

Use when

Install

Models it drives: p-video-avatar

Example output

https://skills.varg.ai/previews/inference-sh-p-video-avatar.mp4 — P-Video-Avatar output from the launch reel on inference.sh's blog: a presenter generated from one portrait, lip-synced with built-in TTS (burned-in captions from the reel) (credit: Pruna AI × inference.sh (P-Video-Avatar launch reel), https://inference.sh/blog/guides/p-video-avatar-talking-head-generation)

More talking heads & avatars skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.