ElevenLabs Voice Isolator (inference.sh) — model skill for sound effects

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.

Remove background noise and isolate vocals from any recording with ElevenLabs, via inference.sh.

What it does

Runs the ElevenLabs voice isolator through inference.sh for noise removal, voice extraction and audio cleanup. Typical uses are podcasts, interviews, music vocals and noisy recordings.

Use when

Install

Example output

https://skills.varg.ai/previews/inference-sh-elevenlabs-voice-isolator.mp3 — Audio of ElevenLabs' Voice Isolator demo: a man speaking on a noisy rooftop; about 6 s in the 'Voice isolated' toggle switches on and the background noise drops away (credit: ElevenLabs (Voice Isolator demo), https://elevenlabs.io/voice-isolator)

More sound effects 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.