Appndo
by 101-skillsDesign

AI Avatar Video

Creates talking-head and avatar videos from portraits paired with scripts or audio, with options for voice, language, style, and lip sync.

What this skill does

The skill turns a portrait into an AI-presented video using either a written script with text-to-speech or an existing audio track. It can select among several avatar and lip-sync models for different needs, including multi-character scenes and realistic synchronization. It also supports workflows for generating portraits, producing speech for models without built-in TTS, dubbing videos into other languages, and creating batches of presenter-led content.

Try it with a task

Example request to give your agent after installation.

Create a 30-second vertical product explainer from my presenter portrait and English script, using an enthusiastic female voice, natural gestures, a studio background, and 1080p output.

Before you start

Requires the inference.sh command-line tool (`belt`), the belt CLI skill, and authentication through `belt login`. Generation also needs a suitable portrait image URL and either a script or an audio URL, depending on the selected model.

Original SKILL.md

Version a623d475 · fetched Oct 19, 2026 · No open license is stated, so the original text is not reproduced here.

Related skills

  • AI Video Generationby 101-skills · Design

    Generates and edits AI videos from text, images, references, video, and audio using models available through the inference.sh CLI.

    806Kinstalls

  • AI Image Generationby 101-skills · Design

    Generates and edits images with dozens of AI models through the inference.sh command-line interface.

    805.1Kinstalls

  • Twitter Automationby 101-skills · Automation

    Automates X posts, media publishing, likes, reposts, direct messages, follows, profile lookups, and post retrieval or deletion.

    804.9Kinstalls