A complete AI voice solution for generating lifelike text-to-speech and performing accurate speech-to-text transcription via ElevenLabs.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install elevenlabs-voice
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-voice 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 Speech?
The ElevenLabs Speech skill provides a robust interface for both Text-to-Speech (TTS) and Speech-to-Text (STT) capabilities powered by ElevenLabs AI. It allows developers to generate lifelike human voices from text or transcribe audio files into text with high accuracy. This skill is ideal for building interactive voice agents, automated content creation, and multi-language communication tools. By utilizing Openclaw Skills, you can seamlessly integrate advanced audio processing into your existing workflows to create more immersive user experiences.
ElevenLabs Speech Use Cases
- Generating natural-sounding voiceovers for videos, presentations, or automated responses.
- Transcribing voice messages from messaging platforms like Telegram for further processing.
- Building interactive voice-controlled AI assistants that can both listen and speak.
- Providing accessibility features by converting written text into spoken audio for users.
- Localizing content with high-quality AI voices across 99 supported languages.
How ElevenLabs Speech Works
- The system authenticates with the ElevenLabs API using a secure API key stored in environment variables.
- For Text-to-Speech, the skill sends a text payload to ElevenLabs, selecting a specific Voice ID and model (like Turbo v2.5).
- The API returns a high-quality audio stream which is saved as an MP3 or WAV file locally.
- For Speech-to-Text, the Scribe engine processes uploaded audio files to generate a precise text transcription.
- Developers can fine-tune the output by adjusting stability and similarity boost parameters for the perfect vocal tone.
ElevenLabs Speech Setup
To get started, set your API key as an environment variable:
export ELEVENLABS_API_KEY="sk_your_api_key_here"
You can also include this in a .env file in your workspace root. To generate speech via the CLI, use:
python scripts/elevenlabs_speech.py tts -t "Hello from Openclaw Skills" -o output.mp3
To transcribe an existing audio file:
python scripts/elevenlabs_scribe.py audio_sample.ogg
ElevenLabs Speech Data Schema & Taxonomy
The skill manages audio data and metadata through the following structure:
| Attribute | Description | Format |
|---|---|---|
| Voice ID | Unique identifier for a specific AI voice (e.g., Rachel, Josh) | String |
| Stability | Controls the emotional range and consistency of the voice | Float (0.0 - 1.0) |
| Similarity | Determines how closely the output matches the original voice | Float (0.0 - 1.0) |
| Audio Formats | Supported files for STT and TTS output | mp3, ogg, wav, m4a |
| Language Code | Optional hint for STT transcription accuracy | ISO 639-1 (e.g., eng, spa) |
ElevenLabs Speech Advanced Features
- Support for speaker diarization to detect and separate multiple speakers in a single recording.
- Access to the eleven_multilingual_v2 model for superior performance in non-English languages.
- Low-latency generation using the eleven_turbo_v2_5 model for real-time applications.
- Seamless integration with the Telegram message tool to send voice replies automatically.
- Automatic language detection for Speech-to-Text covering 99 different languages.
SKILL.md
Loading
Related Openclaw Skills
Dog Potty Training Assistant
A comprehensive behavioral correction system for adult dog potty training that tracks logs, provides reminders, and analyzes progress.
Session History
A powerful retrieval tool designed to search and browse past conversation transcripts across all agent sessions.
Job Search MCP
A powerful multi-platform job aggregator skill that enables AI agents to search, filter, and compare listings across eight global job boards simultaneously.
Web Publish
Instantly transform local Markdown or HTML files into shareable, expiring web links for easy mobile access.
Resume Builder for Reactive Resume
A conversational AI tool that generates professional, schema-compliant resumes specifically for the Reactive Resume platform.
TTS (Text-to-Speech)
A versatile text-to-speech skill that converts agent text responses into professional-grade MP3 audio files.
Featured*
