skills.rest
Aadi-110i
Aadi-110iCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

ai-avatar-video

Generate AI avatar and talking head videos via the inference.sh CLI.

Updated Jul 28, 2026
Search Tags:#text-to-speech#video generation#dubbing#inference.sh#lipsync#talking head#ai avatar
One-click install
npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill ai-avatar-video-aadi-110i
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ai-avatar-video
Source: https://github.com/Aadi-110i/PEP-PROJECT/tree/main/skills/ai-avatar-video
Command: npx skills add https://github.com/Aadi-110i/PEP-PROJECT --skill ai-avatar-video-aadi-110i

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Creating presenter-style videos traditionally requires cameras, actors, and editing time. This Skill lets you generate talking head and avatar videos directly from a portrait image plus a script or audio file, using hosted AI models through the inference.sh CLI. ## Core Features & Use Cases - Multiple Avatar Models: Choose from P-Video-Avatar (fast, low-cost, built-in TTS with 30 voices and 10 languages), OmniHuman 1.5 (multi-character), Fabric 1.0, and PixVerse Lipsync. - Text-to-Avatar with Built-in TTS: P-Video-Avatar converts a text script directly into a spoken avatar video, with voice, language, style, and resolution controls up to 1080p. - Full Pipelines: Combine portrait generation, TTS, transcription, translation, and lipsync to build dubbing and localization workflows. - Use Case: A marketing team needs a product demo video in three languages. They generate a portrait with pruna/p-image, create the avatar video with P-Video-Avatar, then use Whisper transcription and LatentSync lipsync to dub localized versions. ## Quick Start Ask the AI to create a talking avatar video from a portrait image URL and a short voice script using the P-Video-Avatar model via the belt CLI.

Frequently Asked Questions about ai-avatar-video

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create a talking head video from a photo and text?▼

Run pruna/p-video-avatar via the belt CLI with an image URL and a voice_script field. The model has built-in TTS with 30 voices across 10 languages, so no separate audio generation step is needed.

Which AI avatar model should I use for lipsync videos?▼

P-Video-Avatar is the recommended default at roughly 1.83 seconds of processing per second of video and $0.025 per second. OmniHuman 1.5 suits multi-character images, Fabric 1.0 handles image-plus-audio talking, and PixVerse Lipsync targets realistic lipsync.

Can I use my own audio instead of text-to-speech?▼

Yes. P-Video-Avatar accepts an audio field with a speech file URL instead of voice_script. OmniHuman, Fabric, and PixVerse Lipsync require an audio_url input since they lack built-in TTS.

How do I dub an existing video into another language?▼

Transcribe the original with infsh/fast-whisper-large-v3, translate the text, generate new speech with infsh/kokoro-tts, then lipsync the original video to the new audio using infsh/latentsync-1-6.

What are the limitations of AI avatar generation?▼

Results depend on input quality: use front-facing portraits with good lighting and clean audio with minimal background noise. Non-TTS models require a separate speech generation step, and P-Video-Avatar's output aspect ratio matches the input image.

Related Skills

Explore More Content & Communication Skills→
inference-shinference-sh
723

p-video-avatar

Generate talking head avatar videos from portrait images using Pruna P-Video-Avatar via the inference.sh CLI.

Official
Intermediate
Pika-LabsPika-Labs
38

language-swap

Translate and dub videos into another language while preserving the original speaker's voice.

Official
Advanced
JosiahSiegelJosiahSiegel
51

fal-audio

Transcribe audio, translate speech, synthesize voices, and clone voices.

Community
Advanced
framerslabframerslab

video-generation

Generates videos from text or images and analyzes scenes with object detection.

Official
Advanced