elevenlabs/skills

Collections of skills for building with ElevenLabs

What it is

ElevenLabs Skills is a collection of ready‑to‑use agent skills that let an AI coding assistant call ElevenLabs’ speech‑AI services. Each skill is a small, self‑contained module (e.g., text‑to‑speech, speech‑to‑text, voice‑changing, music generation) that follows the open Agent Skills specification so they can be plugged into any compatible LLM‑or‑chat‑agent platform.

Why it matters

ElevenLabs provides high‑quality, lifelike voice synthesis and related audio tools. By packaging those capabilities as standardized skills, developers can quickly add voice interaction, transcription, dubbing, or music generation to their agents without writing low‑level API calls. The repo also ships evaluation scripts to verify that the skills fire correctly and produce the expected outputs.

Core components

Component Role
Skill directories (text-to-speech, speech-to-text, agents, …) Each contains the implementation, usage examples, and a references/ folder with SDK‑specific setup instructions.
Installation script (npx skills add elevenlabs/skills) One‑line command that registers the whole skill set with the user’s AI‑coding‑assistant environment.
Configuration Requires an ELEVENLABS_API_KEY environment variable; the onboarding and setup-api-key skills help manage this automatically.
SDK support Example code for Python (elevenlabs), JavaScript/TypeScript (@elevenlabs/elevenlabs-js), and a CLI wrapper (@elevenlabs/cli or Homebrew).
Evaluations (evals/) Automated trigger and functional tests that run via a Python script, using the Cursor Agent CLI to simulate real‑world usage.
License MIT, allowing free reuse and modification.

Who should use it

  • AI developers building voice‑enabled assistants, chatbots, or multimodal agents who want a plug‑and‑play way to call ElevenLabs services.
  • Product teams needing quick prototypes for speech synthesis, transcription, dubbing, or AI‑generated music.
  • Researchers who want a reproducible benchmark of ElevenLabs‑based audio capabilities, thanks to the built‑in evaluation suite.

Getting started

  1. Install the skill pack: npx skills add elevenlabs/skills.
  2. Run the onboarding skill or manually set ELEVENLABS_API_KEY.
  3. Pick a skill (e.g., text-to-speech) and follow the language‑specific examples in its references/ folder.
  4. Optionally run the test suite: python3 evals/run_all.py -v.

All details above are taken directly from the repository’s README.

Related

  • Project
    elevenlabs/elevenlabs-python

    The ElevenLabs Python SDK is an official library that enables developers to integrate high-quality text-to-speech, voice cloning, and real-time conversational AI agents into their applications.

  • Project
    elevenlabs/elevenlabs-js

    The official Node.js SDK for ElevenLabs, enabling developers to integrate lifelike AI voice synthesis, real-time audio streaming, and voice-powered AI agents into their applications.

  • Project
    liyupi/ai-promo-video-maker

    An open‑source tool that lets you describe a product in one sentence and, using LLM agents, automatically researches, designs style frames, captures 4K screenshots, generates music/voice (ElevenLabs optional), assembles scenes with Remotion, validates timing and audio, and outputs a finished promotional video.

  • Project
    openclaw/agent-skills

    OpenClaw Agent Skills is a reusable library of workflow “skills” (e.g., autoreview, behavior validation, session viewer) for AI coding agents in OpenClaw projects. It provides a Python installer to symlink or copy these skills into a user’s agent‑skill directory, enabling consistent, version‑controlled automation across repositories. Includes validation scripts, MIT licensing, and support for Codex/Claude agents.