ElevenLabs Skills
Ten skills from ElevenLabs: text to speech, transcription, voice agents, sound effects, music, dubbing and voice cleanup through the API
- 516 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The agent calls the ElevenLabs cloud API with your key, and calls are billed
- Texts and audio from your projects are sent to ElevenLabs for voiceover, transcription and dubbing
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/elevenlabs-skillsDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The agent calls the ElevenLabs cloud API with your key, and calls are billed
- Texts and audio from your projects are sent to ElevenLabs for voiceover, transcription and dubbing
This is third-party code. Review the repository files before installing.
What it does
ElevenLabs Skills is the official skill set for developers who add ElevenLabs voice AI to their apps. The agent gets working examples in Python, JavaScript and the CLI and has less to guess about API parameters. There are ten skills. text-to-speech turns text into speech with ElevenLabs voices, in 90-plus languages according to the skill description. speech-to-text transcribes audio with timestamps, and speech-engine adds live voice conversation to your own language model or chat agent. The agents skill builds conversational voice agents, sound-effects makes sound effects from a description, and music composes tracks. voice-changer turns speech into a different target voice, voice-isolator strips background noise and keeps the speech, and dubbing dubs audio and video into other languages while keeping the speakers' voices. A separate setup-api-key skill walks through getting and configuring a key. Every skill reads the key from the ELEVENLABS_API_KEY variable. The evals folder holds checks for whether a skill triggers on the right queries and produces the right output.
Who it is for. For developers of voice apps, bots and voiceover tools, video editors and podcasters who write code with an agent.
Good fit when
- The app needs voiceover: the agent writes a text-to-speech call in Python or JavaScript with the right model and voice
- Meeting or interview recordings must become text with timestamps
- You are building a voice assistant and connect live conversation to your own language model through speech-engine
- A video or podcast should be dubbed into other languages while keeping the speakers' voices
- A recording has background noise and only the speech should stay
Not a fit when
- You want voiceover without an ElevenLabs account and key: every skill goes through the platform and needs a key
- The task is solved by a local model offline: the skills require network access
- You are looking for voice conversation with the agent itself in the terminal: the set targets building voice features into your projects
- You need examples for another vendor's service: the skills cover the ElevenLabs API only
Example request
Add a "Read the article aloud" button to my Next.js app: a server route should send the text to ElevenLabs and return an mp3. Use the text-to-speech skillLimitations
Every skill needs an ElevenLabs key and internet access; the key goes in the ELEVENLABS_API_KEY variable. ElevenLabs bills API usage, so check their site for terms. For JavaScript install @elevenlabs/elevenlabs-js; the elevenlabs package on npm belongs to the outdated 1.x line.
Examples default to the eleven_v4 model, which is worth checking against the vendor's current model list. Running the evals folder requires Cursor Agent CLI and Cursor authentication.
How to disable. Delete the skill folders from the agent's skills directory (for example .claude/skills/ or .agents/skills/). Remove the ELEVENLABS_API_KEY variable from your shell profile and revoke the key in the ElevenLabs dashboard.
FAQ
How do I install the ElevenLabs skills in Claude Code or Cursor?
Run npx skills add elevenlabs/skills. The skills.sh installer detects supported agents and places the skills in the right folders. Then set your key with export ELEVENLABS_API_KEY="your-key".
Which skills are in the ElevenLabs set?
Ten: text-to-speech, speech-to-text, speech-engine, agents, sound-effects, music, voice-changer, voice-isolator, dubbing and setup-api-key. Each sits in its own folder with a SKILL.md and references.
How is speech-engine different from the agents skill?
speech-engine adds live voice conversation to your own language model or chat agent. The agents skill builds conversational voice agents on the ElevenLabs platform.
Which ElevenLabs package should I install for JavaScript?
@elevenlabs/elevenlabs-js. The authors warn that npm install elevenlabs pulls the outdated 1.x line. In Python, use pip install elevenlabs.
How do I get an ElevenLabs API key?
Use the setup-api-key skill, which walks through getting and configuring a key, or open the key page in the ElevenLabs dashboard. The key is read from the ELEVENLABS_API_KEY variable.
Discussion
No questions or reviews yet.
Related
SkillsA skill that teaches the agent to build narrated videos through narrator-ai-cli: source, template, music, voice, script and composing
Local speech synthesis for agents: a command and a skill voice text, clone a voice from a recording and render scores to audio, with no cloud
A set of SKILL.md skills for short-video and content production: topic, script, voice, avatar, editing, covers and motion graphics
YouTube Skills
YouTube Skills for AI Agents
A set of skills that gives an agent YouTube transcripts, video and channel search, and playlist extraction over one API
A skill that turns an idea, a link or a screen recording into finished video: HeyGen avatar, b-roll, captions and quality checks
Twelve skills that make an agent build single-file HTML animations: slides, protocol diagrams, architecture diagrams and demos for screen recording
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| ElevenLabs Skills (this entry) | yes | 516 | ||
| VoiceMode | yes | not required | 1,427 | an MCP server for talking by voice to the agent itself, without skills for a voiceover API |
| Yandex Station TTS skill | no | 1 | reads agent replies aloud with the Alice voice on a Yandex Station over the local network | |
| yovoice | no | 1,968 | local speech synthesis for agents |
README in short
A short README: what the skills are, a one-command install, a table of ten skills with descriptions, key setup through an environment variable and the SDK list (Python, JavaScript, CLI). It also warns about the outdated elevenlabs package on npm and describes the evals folder with trigger and output checks.
README badge
Original SKILL.md
---
name: text-to-speech
description: Convert text to speech using ElevenLabs voice AI. Use when generating audio from text, creating voiceovers, building voice apps, or synthesizing speech in 90+ languages.
license: MIT
compatibility: Requires internet access and an ElevenLabs API key (ELEVENLABS_API_KEY).
metadata: {"openclaw": {"requires": {"env": ["ELEVENLABS_API_KEY"]}, "primaryEnv": "ELEVENLABS_API_KEY"}}
---
# ElevenLabs Text-to-Speech
Generate natural speech from text - supports 90+ languages, multiple models for quality vs latency tradeoffs. Examples default to `eleven_v4`, the latest and highest-quality model.
> **Setup:** See [Installation Guide](references/installation.md). For JavaScript, use `@elevenlabs/*` packages only.
## Quick Start
### Python
```python
from elevenlabs import ElevenLabs
client = ElevenLabs()
audio = client.text_to_speech.convert(
text="Hello, welcome to ElevenLabs!",
voice_id="JBFqnCBsd6RMkjVDRZzb", # George
model_id="eleven_v4"
)
with open("output.mp3", "wb") as f:
for chunk in audio:
f.write(chunk)
```
### JavaScript
```javascript
import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { createWriteStream } from "fs";
import { Readable } from "stream";