A comprehensive ElevenLabs-powered voice studio for OpenClaw providing professional 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 clawvox
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 clawvox 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 ClawVox?
ClawVox is a sophisticated audio production suite designed for the OpenClaw ecosystem, leveraging the industry-leading ElevenLabs API. It enables developers and users to generate lifelike speech, transcribe audio with high accuracy, and even clone specific voices for a personalized AI experience. By integrating these professional-grade audio tools, ClawVox expands the capabilities of Openclaw Skills, making it possible to build interactive voice assistants, automated narrators, and multilingual content generators within a single interface.
This skill serves as a bridge between powerful generative audio models and your local workspace, offering a collection of optimized shell scripts for complex tasks. Whether you need real-time low-latency speech or high-fidelity multilingual dubbing, ClawVox provides the necessary infrastructure to handle audio assets professionally.
ClawVox Use Cases
- Create high-fidelity voiceovers for videos or presentations using Openclaw Skills.
- Transcribe meetings, podcasts, or voice memos into searchable text automatically.
- Clone your own voice to provide a consistent and personal identity for your AI agent.
- Generate custom sound effects for immersive applications and games.
- Dub existing audio or video content into over 29 different languages while maintaining voice characteristics.
- Isolate clear speech from noisy environments for better processing and clarity.
How ClawVox Works
- The user provides a command through the OpenClaw interface or CLI scripts using their ElevenLabs API key.
- ClawVox processes the request, communicating with the ElevenLabs backend via curl and jq.
- For text-to-speech, the selected model (Flash, Turbo, or Multilingual) synthesizes the audio and saves it to the local directory.
- For transcription or dubbing, the skill uploads the source file, monitors the processing status, and retrieves the resulting text or audio.
- The generated assets are organized within the OpenClaw file structure for immediate use or further automation.
ClawVox Setup
First, obtain an API key from the ElevenLabs dashboard. You can then configure the skill by adding your credentials to your OpenClaw configuration file:
{
"skills": {
"entries": {
"clawvox": {
"apiKey": "YOUR_ELEVENLABS_API_KEY",
"config": {
"defaultVoice": "Rachel",
"defaultModel": "eleven_turbo_v2_5",
"outputDir": "~/.openclaw/audio"
}
}
}
}
}
Alternatively, set the environment variable directly in your terminal:
export ELEVENLABS_API_KEY="your_api_key_here"
Ensure you have jq and curl installed on your system to enable the full range of Openclaw Skills features.
ClawVox Data Schema & Taxonomy
ClawVox manages a variety of audio formats and metadata to ensure seamless integration with Openclaw Skills. The following table describes the typical data output:
| Data Type | Description | Formats |
|---|---|---|
| Generated Speech | Audio output from text-to-speech requests | MP3, WAV |
| Transcripts | Text-to-speech output with optional timestamps | Plain Text, JSON |
| Cloned Voices | Metadata and IDs for custom voice profiles | JSON |
| Sound Effects | Custom generated audio clips | MP3 |
| Dubbing Records | Translation projects and target language audio | MP3, M4A |
ClawVox Advanced Features
- Instant and professional voice cloning with background noise removal during the sample processing phase.
- Multi-language dubbing support for 29+ languages, retaining original voice tone and emotional nuance.
- High-speed streaming with the Flash v2.5 model, reaching latencies as low as 75ms for real-time interactions.
- Fine-grained voice settings to control stability, similarity, and speaking speed for tailored output.
- Batch processing of text files for long-form content like audiobooks, podcasts, or documentation narration.
- Professional voice isolation tools to surgically remove background noise from any audio source via Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Outlook CLI
A professional command-line interface for Microsoft Outlook that enables listing, searching, reading, and sending emails via the Microsoft Graph API.
Toingg Ops Toolkit
A full-featured automation suite for managing Toingg voice campaigns and WhatsApp messaging workflows through the Openclaw Skills framework.
Toingg Ops Toolkit
A comprehensive toolkit for managing Toingg voice and WhatsApp outreach campaigns through automated scripts and scheduled analytics.
MS Outlook + Teams Assistant
A desktop-first assistant that monitors Outlook and Teams to track action items and draft concise, personable replies.
Zerion API Skill
A comprehensive crypto intelligence tool for querying multi-chain portfolios, DeFi positions, and transaction history via the Zerion MCP server.
Zerion API Skill
A powerful MCP-enabled skill for real-time querying of crypto wallet data, DeFi positions, and token pricing across EVM chains and Solana.
Featured*
