ElevenLabs Skills Agent skills for ElevenLabs developer products. These skills follow the Agent Skills specification and can be used with any compatible AI coding assistant. Installation [安装/使用命令见下方] Available Skills Skill Description text to speech Convert text to lifelike speech using ElevenLabs' AI voices speech to text Transcribe audio files to text with timestamps speech engine Add real time voice conversations to a custom LLM or chat agent agents Build conversational voice AI agents sound effects Generate sound effects from text descriptions music Generate music tracks using AI composition voice changer Transform the voice in an audio recording into a different target voice (speech to speech) voice isolator Remove background noise and isolate vocals/speech from audio setup api key Guide through obtaining and configuring an ElevenLabs API key Configuration All skills require an ElevenLabs API key. Set it as an environment variable: [安装/使用命令见下方] Get your API key from the setup api key skill or use the ElevenLabs dashboard. SDK Support Most skills include examples for: Python pip install elevenlabs JavaScript/TypeScript npm install @elevenlabs/elevenlabs js cURL Direct REST API calls JavaScript SDK Warning: Always use @elevenlabs/elevenlabs js . Do not use npm install elevenlabs (that's an outdated v1.x package). See the installation guide in any skill's references/ folder for complete setup instructions including migration from deprecated packages. Evaluations The evals/ directory contains trigger and functional evaluations for all skills. [安装/使用命令见下方] Results are saved to evals/results/ / with a report.md summary and results.json for programmatic access. Functional 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. Requires the Cursor Agent CLI ( cursor agent on your PATH ; override binary with CURSOR AGENT ) and Cursor authentication ( cursor agent login or CURSOR