ElevenLabs TTS (inference.sh) — model skill for voice & voiceover

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.

Voice scripts with ElevenLabs v4, v4 Turbo, v3, Multilingual v2 and Flash, via inference.sh.

What it does

Runs ElevenLabs text-to-speech through inference.sh, with each model as its own app: Eleven v4 and v4 Turbo (audio tags, realtime streaming), Eleven v3, Multilingual v2 and Flash v2.5. It includes voice selection guidance.

Use when

Install

Models it drives: eleven_v4, eleven_v4_turbo, eleven_v3, eleven_multilingual_v2, eleven_flash_v2_5

Example output

https://skills.varg.ai/previews/inference-sh-elevenlabs-tts.mp3 — Eleven v4 (the skill's default model) narration steered with audio tags like [tense] and [whispering]: 'The night was quiet, almost unnaturally so. Then I heard the old gate creak open behind me…' (credit: ElevenLabs (Eleven v4 sample), https://elevenlabs.io/blog/emotional-text-to-speech-with-eleven-v4)

More voice & voiceover 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.