Agent Tooling
Tools for agents to build with ElevenLabs.
Overview
Section titled “Overview”Agent tooling includes reusable skills and local integrations that help you automate ElevenLabs workflows in developer tools and assistants.
Agent skills
Section titled “Agent skills”Agent Skills are reusable building blocks for common ElevenLabs workflows. They follow the Agent Skills specification and can be used with compatible coding assistants. Install the skills with:
npx skills add elevenlabs/skillsThe official collection is hosted in the elevenlabs/skills repository. Open each skill for a prompt you can paste into your assistant after installing the skills.
Text to speech
Convert text to speech using ElevenLabs voices.
Use the text to speech skill to generate audio for the script below.
Model: eleven_v4
Voice: "Juniper" (or default).
Output: Save the MP3 file locally and return the file path.
Script: "Welcome to ElevenLabs. Today we will walk through the new agent tooling."Speech to text
Transcribe audio to text with timestamps.
Use the speech to text skill to transcribe the audio file path/to/file.mp3.
Return a transcript that contains speaker IDs and timestamps at the start of each paragraph.Realtime speech to text
Stream live transcription with low latency.
Use the speech to text skill to start a real-time transcription session for microphone input.
Model: scribe_v2_realtime.
Stream partial transcripts and return committed transcripts with word-level timestamps.Agents
Build conversational voice agents.
Use the Agents skill to create a voice agent named "Support Concierge".
Persona: friendly, concise, asks clarifying questions when needed.
Goals: answer pricing questions and route enterprise leads to sales.Speech Engine
Add voice to a custom chat agent using the Speech Engine skill.
Use the Speech Engine skill to add voice to my chat agent.
Server: Node.js with an existing HTTP server.
LLM: Use my existing chat completion logic.
Output: Create the Speech Engine server route, client connection code, and setup steps.Sound effects
Generate sound effects from text prompts.
Use the Sound effects skill to generate a 3-second effect: "Wooden door creaks open, then a soft slam."
Output WAV at 48 kHz and return the file path.Music
Generate music tracks from prompts.
Use the Music skill to generate a 30-second instrumental loop.
Style: lo-fi hip hop, warm, chill.
BPM: 80. No vocals.
Return the audio file path.Voice changer
Transform a recording into a different target voice while preserving the original delivery.
Use the voice changer skill to transform path/to/file.mp3 into the voice "George".
Model: eleven_multilingual_sts_v2.
Return the transformed audio file path.Voice isolator
Remove background noise from audio files.
Use the voice isolator skill to remove background noise from path/to/file.mp3.
Return the cleaned audio file path.Setup API key
Get and configure an ElevenLabs API key.
How do I get my ElevenLabs API key?ElevenLabs MCP server
Section titled “ElevenLabs MCP server”The hosted MCP server is a remote Model Context Protocol server so assistants like Claude can manage your agents through simple prompts. It uses OAuth sign-in with your ElevenLabs account and requires no local installation. Connect from the Claude Desktop directory.
Hosted MCP server
Connect from the Claude Desktop directory. No installation required.