⏳ This skill is pending AI review.
Scores will appear once the review pipeline completes.
realtime
Use ElevenLabs Realtime models (`eleven_realtime_v1_mini`, `eleven_realtime_v1_max`), the low-latency models built for voice conversation. Use when the user wants to create an ElevenAgents agent on a Realtime model or switch an existing agent's Voice mode to Realtime, set `conversation_config.realtime_model`, choose between Realtime Mini and Max, or debug a Realtime agent that won't publish or transfer. Also use when migrating a voice app built on OpenAI's Realtime API and SDK (`@openai/agents-realtime`, `gpt-realtime`) to the OpenAI-compatible ElevenLabs Realtime API, including the `client_secrets` mint, the WebSocket transport, and audio after leaving WebRTC (closes with 4001/4003, no audio). Not for choosing an agent's LLM or TTS model in Custom mode, Scribe realtime speech-to-text, or migrating Chat Completions or Responses API text calls.
Choose how to use this skill
You do not need every option. Choose the path your AI client supports. The stable page stays the same; versioned files are immutable.
1. Native installer
This listing has no registered native installer command. Use the complete package or source fallback below, depending on what your client supports.
Do not guess an installer command or replace an existing version without reviewing the diff.
2. Complete package recommended
Download the ZIP when available. It includes SKILL.md plus the references, security notes and version metadata.
No complete ProSkills package is published for this listing yet.3. Prompt-only
Copy the prompt above when the agent can read the stable page or when you want to adopt the workflow without installing a skill.
Need only the instruction file?
Download SKILL.md only if your client requires a single file. The complete ZIP is safer for a full installation because it preserves the references and release context.
No path installs or executes anything by itself. Your agent still needs access to the project files. Before updating, compare the installed version and review the diff.
// RATINGS
Not yet listed on ClawHub or SkillsMP
// README
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
npx skills add elevenlabs/skills
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 |
| realtime | Run agents on ElevenLabs Realtime models, or migrate an OpenAI Realtime voice app to them |
| 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 |
| dubbing | Dub audio/video into other languages while preserving the original speakers' voices |
| onboarding | Add ElevenLabs to a project from scratch: sign-in, API key, SDK and a first request |
| setup-api-key | Fix or hand-configure an existing ElevenLabs API key |
Configuration
All skills require an ElevenLabs API key in ELEVENLABS_API_KEY. The onboarding skill puts one in your project's env file for you. To set one by hand:
export ELEVENLABS_API_KEY="your-api-key"
Keys come from the API keys page; the setup-api-key skill helps with an existing key that stopped working or was issued by an administrator.
SDK Support
Most skills include examples for:
- Python -
pip install elevenlabs - JavaScript/TypeScript -
npm install @elevenlabs/elevenlabs-js - CLI -
npm install -g @elevenlabs/cliorbrew install elevenlabs/tap/elevenlabs(wraps the REST API; readsELEVENLABS_API_KEYautomatically)
JavaScript SDK Warning: Always use
@elevenlabs/elevenlabs-js. Do not usenpm 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.
# Run all evaluations (trigger + functional)
python3 evals/run_all.py -v
# Trigger evals only — tests if skills fire for the right queries (~3 min)
python3 evals/run_all.py --trigger-only -v
# Functional evals only — tests if skills produce correct output (~15 min)
python3 evals/run_all.py --functional-only -v
# Specific skills
python3 evals/run_all.py --skills text-to-speech agents -v
# Custom model (see `cursor-agent --list-models`)
python3 evals/run_all.py --model gpt-5.4-high -v
Results are saved to evals/results/<timestamp>/ 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_API_KEY).
License
MIT
// HOW IT'S BUILT
KEY FILES