ElevenLabs Skills 🧩 Workflow Open source

What it is

ElevenLabs publishes this MIT-licensed set of Agent Skills so coding agents can use its audio APIs correctly. Skills cover text-to-speech, speech-to-text with timestamps, sound effects, music generation, voice changing, voice isolation, dubbing into other languages while keeping the speaker's voice, and conversational voice agents. Each skill includes SDK examples for Python, JavaScript and the ElevenLabs CLI, and a setup skill walks you through getting an API key.

Key features

• text-to-speech and speech-to-text skills with current SDK usage
• dubbing skill for multilingual versions of audio and video
• sound-effects and music skills for generated audio
• voice-changer and voice-isolator for cleaning and transforming recordings
• agents and speech-engine skills for voice assistants
• Evaluation suite that tests triggering and outputs

How to install

Run npx skills add elevenlabs/skills, then set ELEVENLABS_API_KEY in your environment. The skills follow the Agent Skills specification and work in Claude Code, Cursor, Codex and other compatible agents.

Pricing and rights

The skills are free (MIT), but every call uses your ElevenLabs account credits. ElevenLabs' free plan is for non-commercial use with attribution; commercial rights come with paid plans, so check your plan before publishing generated audio.

Who it is for

Developers and creators who script voiceovers, podcasts, dubbing or sound design from an agent instead of the ElevenLabs web app.

Verdict

A small but official and well-tested pack that stops agents from using outdated SDKs. It only covers ElevenLabs, and usage costs sit on your ElevenLabs bill.