← Back to Skills Marketplace
7241
Downloads
16
Stars
29
Active Installs
15
Versions
Install in OpenClaw
/install elevenlabs-voices
Description
High-quality voice synthesis with 18 personas, 32 languages, sound effects, batch processing, and voice design using ElevenLabs API.
Usage Guidance
Install only if you are comfortable sending selected text, sound prompts, and your ElevenLabs API key to ElevenLabs. Use a dedicated API key with quota limits, prefer environment variables over plaintext config files, avoid sensitive content, and be careful with batch files or output paths because they can write files outside the intended output folder.
Capability Analysis
Type: OpenClaw Skill
Name: elevenlabs-voices
Version: 2.1.6
The OpenClaw AgentSkills bundle for ElevenLabs Voices appears to be a legitimate wrapper for the ElevenLabs API, providing text-to-speech, sound effects, and voice design functionalities. It correctly handles API keys via environment variables or a local `.env` file and communicates exclusively with the official ElevenLabs API endpoints. However, the `scripts/sfx.py`, `scripts/tts.py`, and `scripts/voice-design.py` scripts are vulnerable to path traversal. User-provided arguments for `--output` and the `output` field in batch JSON files are used directly to construct file paths for saving audio, without apparent sanitization. This could allow a malicious actor to write files to arbitrary locations on the filesystem (e.g., `../../../../tmp/malicious.mp3`), posing a significant risk of arbitrary file write, which is classified as a vulnerability rather than intentional malice.
Capability Assessment
Purpose & Capability
The scripts are coherent with the stated purpose: text-to-speech, sound effects, and voice design through official ElevenLabs API endpoints, with user-directed audio output and usage tracking.
Instruction Scope
The documentation includes broad natural-language triggers and does not consistently make clear that user text, prompts, and API keys are sent to ElevenLabs for processing and authentication.
Install Mechanism
No package install or hidden install behavior was found; the skill requires python3 and an ElevenLabs API key via environment variables or a local .env file.
Credentials
The scripts accept output filenames from CLI arguments and batch JSON entries and use them directly, allowing path traversal or absolute paths to write audio outside the chosen output directory.
Persistence & Privilege
The setup wizard stores an API key in config.json while the runtime scripts actually read environment variables or .env; docs also claim config.json is gitignored and the key never leaves the machine, but no .gitignore is present and API authentication necessarily transmits the key to ElevenLabs.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install elevenlabs-voices - After installation, invoke the skill by name or use
/elevenlabs-voices - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.1.6
Hardened API key handling and synced OpenClaw metadata/docs.
v2.1.5
Fix: SKILL.md metadata updated to openclaw format. Env vars correctly declared.
v2.1.4
Security: removed config file probing. API key now only from env var or skill-local .env.
v2.1.3
- Added a CHANGELOG.md file to the project.
- Updated documentation in README.md, SKILL.md, and examples.md.
- Modified package.json, scripts/tts.py, and voices.json to reflect documentation or configuration improvements.
- Version bump to 2.1.3.
v2.1.2
Add ClawHub runtime requirements metadata (SKILL.md frontmatter)
v2.1.1
Add runtime requirements metadata for ClawHub discovery
v2.1.0
Version 2.1.0 introduces an interactive setup wizard and improvements for easier first-time use.
- Added `scripts/setup.py` for a guided, interactive configuration wizard on first run (API key, default voice, language, audio quality, cost tracking, budget cap).
- Updated documentation with step-by-step setup and privacy details for configuration.
- Improved descriptions and references for voice and TTS integration (now mentions OpenClaw).
- Minor fixes and updates across scripts and documentation for clarity and onboarding.
- Pronunciation dictionary and configuration process updated for better user experience.
v2.0.4
Migrate from Clawdbot to Moltbot
v2.0.3
chore: update usage tracking and minor fixes
v2.0.2
chore: update usage tracking and minor fixes
v2.0.1
Fix: Update TTS config format for Clawdbot 2026.1.24+ (enabled→auto)
v2.0.0
Major v2.0: 32 languages, streaming, SFX, batch, cost tracker, voice design, pronunciations
v1.1.1
v1.1.1: Python TTS script, 18 voices, 12 presets, multi-accent support
v1.1.0
Added Python TTS script, 18 voices, presets, improved documentation
v1.0.0
Initial release with 14 voice personas across English, German, and Spanish. Includes detailed voice guide and usage examples.
Metadata
Frequently Asked Questions
What is ElevenLabs Voices?
High-quality voice synthesis with 18 personas, 32 languages, sound effects, batch processing, and voice design using ElevenLabs API. It is an AI Agent Skill for Claude Code / OpenClaw, with 7241 downloads so far.
How do I install ElevenLabs Voices?
Run "/install elevenlabs-voices" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ElevenLabs Voices free?
Yes, ElevenLabs Voices is completely free (open-source). You can download, install and use it at no cost.
Which platforms does ElevenLabs Voices support?
ElevenLabs Voices is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ElevenLabs Voices?
It is built and maintained by Robby (@robbyczgw-cla); the current version is v2.1.6.
More Skills