A comprehensive command-line interface for the ElevenLabs AI audio platform supporting text-to-speech, transcription, and voice cloning.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install elevenlabs-cli
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install elevenlabs-cli using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ElevenLabs CLI?
This skill provides a robust CLI client for ElevenLabs, offering 100% SDK coverage for developers and creators. By integrating these Openclaw Skills, users can generate high-quality AI speech, transcribe audio with diarization, and manage voice clones directly from their terminal. It serves as a bridge between local workflows and the powerful ElevenLabs API, enabling seamless audio processing and generation without leaving the command line.
As an unofficial community-maintained tool, it provides flexible access to the entire ElevenLabs ecosystem, including experimental features like sound effect generation and audio isolation. This makes it an essential tool for developers building audio-centric applications or content creators looking to automate their voiceover pipelines using Openclaw Skills.
ElevenLabs CLI Use Cases
- Automating high-quality text-to-speech generation for audiobooks or video narrations.
- Transcribing meetings or interviews with speaker identification and word-level timestamps.
- Creating custom AI voice clones for consistent brand messaging.
- Developing automated dubbing pipelines for multilingual video content.
- Generating immersive sound effects and multi-voice dialogues using Openclaw Skills.
How ElevenLabs CLI Works
- The user installs the CLI and configures their ElevenLabs API key as an environment variable or via the internal configuration command.
- Commands are issued to the CLI (such as tts, stt, or voice) which then prepares the necessary payload including text strings or local audio files.
- The CLI communicates with the ElevenLabs API endpoint over a secure connection, passing the authenticated API key.
- The ElevenLabs infrastructure processes the request using advanced neural models and returns the generated audio, transcription data, or metadata.
- The CLI saves the output to the local file system in various formats or displays the results in the terminal, completing the workflow within the Openclaw Skills ecosystem.
ElevenLabs CLI Setup
Installation is straightforward across multiple platforms. For macOS or Linux users, use Homebrew:
brew tap hongkongkiwi/tap
brew install elevenlabs-cli
For Rust developers, install via Cargo:
cargo install elevenlabs-cli
After installation, configure your API key to start using Openclaw Skills:
# Set API key via environment variable
export ELEVENLABS_API_KEY="your-api-key"
# Or save to permanent config file
elevenlabs config set api_key your-api-key
ElevenLabs CLI Data Schema & Taxonomy
The skill manages various data types through the following structure:
| Component | Data Type | Description |
|---|---|---|
| Configuration | TOML | Stored in ~/.config/elevenlabs-cli/config.toml for API keys and default models. |
| Audio Output | MP3/WAV/Opus | Generated speech and sound effects saved locally in specified quality formats. |
| Transcription | JSON/SRT | Text data with speaker labels and word-level timestamps for video editing. |
| History | Metadata | Tracking and downloading previous generations via Openclaw Skills. |
| Knowledge Base | URL/PDF | Documents used for RAG-based conversational agents. |
ElevenLabs CLI Advanced Features
- Multi-voice dialogue generation with independent voice assignment per line of text.
- Audio isolation technology for removing background noise from existing recordings.
- Automated voice cloning from directories of audio samples or specific audio files.
- RAG-based knowledge base management for conversational AI agents via Openclaw Skills.
- Real-time recording and transcription directly from the microphone.
- Dubbing engine for translating and synchronizing audio across 29+ languages.
SKILL.md
Loading
Related Openclaw Skills
YouTube Downloader
A high-performance utility for AI agents to download and register high-quality YouTube videos as local assets.
Janitor
An automated maintenance agent designed to keep your AI workspace organized, healthy, and synchronized.
Seedance 2.0 Prompt Generator
A professional-grade prompt engineering engine designed specifically for ByteDance's Seedance 2.0 AI video diffusion model.
Janitor
A background maintenance agent that manages memory consolidation, archives stale data, and ensures workspace organization.
HookCatch
A developer-friendly tool for creating webhook bins and local tunnels to test, inspect, and replay HTTP requests programmatically.
China Weather Forecast (weather-china)
A Python-powered weather skill providing 7-day forecasts and life comfort indices for Chinese cities without requiring an API key.
METADATA
Featured*
