AI Podcast Video — workflow 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.

Generate a multi-person talking-head podcast video from scratch: characters, voices, avatars, stitching.

What it does

Creates multi-person talking-head podcast videos from scratch on inference.sh. Characters come from Gemini image models, voices from Inworld TTS and animation from P-Video-Avatar, and the clips are stitched into one conversation video.

Use when

Install

Models it drives: nano_banana_pro, inworld-tts, p-video-avatar

Example output

https://skills.varg.ai/previews/inference-sh-ai-podcast.mp4 — inference.sh's 'one-shot agent podcast': a multi-speaker AI talking-head podcast (host, the Pruna plum, an Inworld character) made by one agent with P-Video-Avatar + Inworld TTS; cut at the host → plum hand-off (credit: inference.sh (@inference_sh), https://x.com/inference_sh/status/2055777143120859344)

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.