{
  "markdown": "![LOGO](/logo.png)\n\n# ElevenLabs Skills\n\nAgent skills for [ElevenLabs](https://elevenlabs.io) developer products. These skills follow the [Agent Skills specification](https://agentskills.io/specification) and can be used with any compatible AI coding assistant.\n\n## Installation\n\n```bash\nnpx skills add elevenlabs/skills\n```\n\n## Available Skills\n\n| Skill | Description |\n|-------|-------------|\n| [text-to-speech](./text-to-speech) | Convert text to lifelike speech using ElevenLabs' AI voices |\n| [speech-to-text](./speech-to-text) | Transcribe audio files to text with timestamps |\n| [speech-engine](./speech-engine) | Add real-time voice conversations to a custom LLM or chat agent |\n| [agents](./agents) | Build conversational voice AI agents |\n| [sound-effects](./sound-effects) | Generate sound effects from text descriptions |\n| [music](./music) | Generate music tracks using AI composition |\n| [voice-changer](./voice-changer) | Transform the voice in an audio recording into a different target voice (speech-to-speech) |\n| [voice-isolator](./voice-isolator) | Remove background noise and isolate vocals/speech from audio |\n| [dubbing](./dubbing) | Dub audio/video into other languages while preserving the original speakers' voices |\n| [setup-api-key](./setup-api-key) | Guide through obtaining and configuring an ElevenLabs API key |\n\n## Configuration\n\nAll skills require an ElevenLabs API key. Set it as an environment variable:\n\n```bash\nexport ELEVENLABS_API_KEY=\"your-api-key\"\n```\n\nGet your API key from the `setup-api-key` skill or use the [ElevenLabs dashboard](https://elevenlabs.io/app/settings/api-keys).\n\n## SDK Support\n\nMost skills include examples for:\n\n- **Python** - `pip install elevenlabs`\n- **JavaScript/TypeScript** - `npm install @elevenlabs/elevenlabs-js`\n- **CLI** - `npm install -g @elevenlabs/cli` or `brew install elevenlabs/tap/elevenlabs` (wraps the REST API; reads `ELEVENLABS_API_KEY` automatically)\n\n> **JavaScript SDK Warning:** Always use `@elevenlabs/elevenlabs-js`. Do not use `npm install elevenlabs` (that's an outdated v1.x package).\n\nSee the installation guide in any skill's `references/` folder for complete setup instructions including migration from deprecated packages.\n\n## Evaluations\n\nThe `evals/` directory contains trigger and functional evaluations for all skills.\n\n```bash\n# Run all evaluations (trigger + functional)\npython3 evals/run_all.py -v\n\n# Trigger evals only — tests if skills fire for the right queries (~3 min)\npython3 evals/run_all.py --trigger-only -v\n\n# Functional evals only — tests if skills produce correct output (~15 min)\npython3 evals/run_all.py --functional-only -v\n\n# Specific skills\npython3 evals/run_all.py --skills text-to-speech agents -v\n\n# Custom model (see `cursor-agent --list-models`)\npython3 evals/run_all.py --model gpt-5.4-high -v\n```\n\nResults are saved to `evals/results/<timestamp>/` with a `report.md` summary and `results.json` for programmatic access.\n\nFunctional evals use an isolated `cursor-agent` workspace per test case (under that results tree); they do **not** modify skill sources under each skill’s directory.\n\nRequires the [Cursor Agent CLI](https://cursor.com/docs/cli/using) (`cursor-agent` on your `PATH`; override binary with `CURSOR_AGENT`) and Cursor authentication (`cursor-agent login` or `CURSOR_API_KEY`).\n\n## License\n\nMIT\n",
  "bytes": 3339,
  "sha": "9e777e9b37997be5cd81937431057ecb331c27324933546aeb7b030f550fc318",
  "repo_slug": "elevenlabs/skills",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/skl_elevenlabs_skills_speech_to_text_464b3181/readme"
}