p-video-avatar Skill (inference.sh) for Claude Code: What It Does and How to Install It

Lets Claude turn a portrait image into a talking avatar video with Pruna P-Video-Avatar, using built-in voices or your own audio.

Installs: 13K; on skills.sh
Stars: 17; on GitHub
Updated: Aug 2026; last repo commit

This skill makes Claude call the pruna/p-video-avatar app with belt app run. Give it a portrait and either a script (30 built-in voices across 10 languages) or an audio file, and it returns a talking video at 720p or 1080p.

It is a third-party skill, not published by Pruna. It needs belt installed and signed in, and each run uses inference.sh credits.

Good for

Marketers and course makers who want an AI presenter from one portrait
Teams localizing one talking-head video into other languages

Install p-video-avatar

Claude Code

Copy this prompt.

Install the p-video-avatar skill in Claude Code. Run this command:

npx skills add https://github.com/inference-sh/skills --skill p-video-avatar

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Requires Node.js.

Pick one route for the skill, then install the belt CLI with one of the belt routes and run belt login. Every command in SKILL.md is a belt app run call, and its allowed-tools line is Bash(belt *), so the skill does nothing without belt. The folder holds 1 file, SKILL.md (repo tree). It runs belt in a shell, so there is no Claude app upload route.

Built from the package data we hold. Not yet tested by us.

What's in the skill

When it loads

Generate talking head avatar videos with Pruna P-Video-Avatar via inference.sh CLI. Turn a portrait image into a realistic speaking video with built-in TTS. 18x faster and 6x cheaper than competitors. Models: P-Video-Avatar, P-Image (for portrait generation). Capabilities: text-to-avatar, audio-driven avatars, 30 voices, 10 languages, 720p/1080p, built-in TTS, dynamic backgrounds, full-body control. Use for: AI presenters, product demos, explainer videos, virtual influencers, marketing, education, multilingual content, UGC, gaming avatars. Triggers: avatar video, talking head, ai avatar, p-video-avatar, pruna avatar, video avatar, ai presenter, digital human, virtual presenter, lipsync, talking avatar, ai spokesperson, heygen alternative, synthesia alternative, veed alternative, fabric alternative, omnihuman alternative

Sections in SKILL.md

Quick Start
Full Workflow: Generate Portrait + Avatar Video
Examples
Text Script with Voice Selection
Audio-Driven Avatar
1080p with Custom Style
Multilingual Content
Reproducible Generation
Available Voices
Supported Languages
Parameters
Pricing
Free Launch Weekend
Competitive Advantage
Use Cases
Tips

Key facts

Author: inference.sh (owner of the repo; plugin.json lists inference.sh as author)
License: MIT per plugin.json and the README badge; the repo has no LICENSE file
Installs on skills.sh (101-skills/superpowers listing): 13,048 (Nov 2, 2026)
GitHub stars: 797 for the whole repo (Nov 2, 2026)
Last repo commit: Oct 15, 2026
Audits on skills.sh (101-skills/superpowers listing): Gen Agent Trust Hub: pass, Socket: warn, Snyk: pass
What it includes: 1 file: SKILL.md (from the repo tree)
Needs: The inference.sh belt CLI, signed in with belt login
Allowed tools: Bash(belt *)

What it includes

belt app run pruna/p-video-avatar with image, voice_script and voice
The portrait is an image URL.
Try: “Make this portrait say a 20-second product intro in a calm male voice”
Runs code · Script to avatar
Make a portrait with pruna/p-image, then animate it
SKILL.md suggests 9:16 for vertical videos.
Runs code · Portrait then avatar
Pass your own audio file; it overrides voice_script
When both are given, audio takes priority.
Runs code · Audio-driven avatar
voice, voice_language, voice_prompt and video_prompt
Set the speaker, language, pacing, emotion, background and body language.
Voice and tone control
14 female and 16 male voices; English US/UK, Spanish, French and more
Counted from the voice and language lists in SKILL.md.
30 voices, 10 languages
720p or 1080p, plus a seed for repeatable results
Output aspect ratio matches the input image.
Resolution and seed
pruna/p-image, pruna/p-video and pruna/p-image-edit
Examples for making portraits and editing images.
Runs code · Related Pruna models

From the official docs

Permissions

Medium risk

This skill makes your agent run belt app run commands that send your prompts and files to inference.sh and use credits on your account. Check the price of an app with belt app pricing before you start a large batch.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Each run uses inference.sh credits
SKILL.md lists $0.025 per second of output at 720p and $0.045 at 1080p, for example $0.75 for a 30-second 720p video. The belt README shows belt balance to check credits and belt app pricing to see the cost formula before a run. github.com
Your prompts and files go to inference.sh
Every belt app run sends its input to an inference.sh app. The belt README says local file paths in an input are uploaded by the CLI. The portrait and any audio you give it are inputs to the app. github.com
The safety filter is listed as off by default
The parameter table lists disable_safety_filter with a default of true and the description "Disable content filter". Our advice: set it to false, and only use portraits of people who agreed. github.com
You must install the belt CLI first
The belt README gives a download-and-review install script, Homebrew, npm and Scoop. cli-install.md in the repo says the installer downloads a binary and checks its SHA-256 checksum. The belt skill named in SKILL.md can also run brew install and npm install -g. github.com

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	SKILL.md describes no read-only mode.
Talks to	inference.sh (belt app run calls). cli.inference.sh and dist.inference.sh (belt installer)
Sign-in and keys	Run belt login to sign in to inference.sh. SKILL.md does not say where belt keeps the login.
Scopes	Runs belt app run commands in your shell (allowed-tools: Bash(belt *)) Uploads the inputs you give it, including local files, to inference.sh

Questions

What does the p-video-avatar skill do?

It makes Claude turn a portrait image into a talking avatar video with Pruna P-Video-Avatar. You supply a script with one of 30 built-in voices in 10 languages, or your own audio, and choose 720p or 1080p.

How do I install it?

Use the install box at the top of this page for the skill. You also need the belt CLI from inference.sh, installed with one of the belt routes in the box, and a belt login. There is no Claude app upload route because the skill runs belt in a shell.

Does it need an account or API key?

It needs an inference.sh sign-in through belt login. SKILL.md names no separate API key. SKILL.md lists $0.025 per second of output video at 720p and $0.045 at 1080p, for example $0.75 for 30 seconds at 720p.

Is it safe?

It runs belt app run commands through your shell. Each run sends your prompt and any files or URLs you give it to inference.sh and uses credits. The belt CLI has to be installed first, so read its install steps before you run them.

Is this a Pruna skill?

No. It is not published by Pruna. The repo owner is inference-sh, and its plugin.json names inference.sh as author. The skill calls a Pruna app hosted on inference.sh.

Who publishes this skill?

inference.sh, in its own repo github.com/inference-sh/skills. The repo's plugin.json lists inference.sh as author and https://inference.sh as homepage.

Is there another copy of this skill?

skills.sh also lists this skill under 101-skills/superpowers, a repo whose plugin.json names inference.sh as author and inference-sh/skills as the repository. This page links to inference-sh/skills, the repo the plugin.json points to.

How much does a video cost?

SKILL.md lists $0.025 per second of output at 720p and $0.045 at 1080p. Its example: a 30-second 720p video is $0.75.

Which languages and voices does it support?

SKILL.md lists 30 voices (14 female, 16 male) and 10 languages: English (US), English (UK), Spanish, French, German, Italian, Portuguese (Brazil), Japanese, Korean and Hindi.

Which other skills does it point to?

Its Related Skills section lists infsh-cli, p-video, p-image, ai-video-generation and ai-image-generation from inference-sh/skills. They are optional.

Information

updated Nov 2, 2026

Repository: inference-sh/skills
Folder: tools/video/p-video-avatar

inference-sh/skills skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 6

p-video-avatar SKILL.md · github.com
belt CLI README · github.com
cli-install.md · github.com
README · github.com
plugin.json · github.com
belt skill SKILL.md · github.com