How to make an AI singer music video with lip-sync — trending format for music videos

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

AI singer music video: the agent writes lyrics, a model makes the song, a generated singer lip-syncs it.

What it does

Use it when someone asks for an AI singer, a singing character or a music video with lip-sync from just a theme. The agent writes the lyrics (verse, chorus, verse, chorus, 60–90 s), generates the song with vocals on lyria_3_5, makes one chest-up portrait of a fictional singer on nano_banana_pro (9:16, stage light), then lip-syncs the still to the song with minimax_h3_max_lipsync, so the video follows the audio length. Optional: 3–4 cutaway shots from the lyrics on seedance_2_5, cut between sung lines on the instrumental bars, and the lyrics as captions. Output is a vertical MP4 as long as the song. For a directed, shot-by-shot video from an existing song use varg-music-video. Run it with varg-ai.

Use when

Status

A format people ask for that has no dedicated skill yet. Make it with the skills on the use-case pages below, or with varg directly.

Example: https://x.com/mo_alani_yes/status/2113344538802819346

How an agent would make it: Claude writes the lyrics → song with vocals (lyria_3_5; the post used Suno) → one portrait still of a fictional singer (nano_banana_pro, 9:16) → lip-sync the still to the song (minimax_h3_max_lipsync) → optional seedance_2_5 cutaways between sung lines → cut, lyrics as captions

Models it drives: lyria_3_5, nano_banana_pro, minimax_h3_max_lipsync, seedance_2_5

More music videos 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.