Elevenlabs

**Judgement:** A feature-rich, well-scoped integration for the ElevenLabs API that gives OpenClaw users practical end-to-end audio generation and management capabilities. Technically strong and broadly useful if you already rely on ElevenLabs. **What it does well** - Wraps most core ElevenLabs services: TTS, SFX, music, voice listing, voice cloning, and quota/usage. - Exposes multiple models and audio formats with clear, concrete CLI examples for typical workflows. - Sensible security hardening for voice cloning input files by default (sample-dir sandbox) to prevent arbitrary file reads. **Key risks / limitations** - **Ethical and legal risk around voice cloning:** The tool enables rapid voice cloning; it does not implement consent checks, identity verification, or misuse detection. Proper governance, permissions, and policy compliance must be handled by the user’s organization. - **Dependency on ElevenLabs cloud service:** Functionality, latency, and reliability are bounded by ElevenLabs’ API availability, rate limits, and account quota. Outages or plan changes will directly impact this skill. - **No visible advanced safety controls:** There is no built-in filtering for harmful/abusive content or guardrails against deepfake-style misuse beyond filesystem sandboxing. **Recommended scenarios** - Teams and developers who already have an ElevenLabs subscription and want scriptable audio generation (voice, SFX, music) inside OpenClaw workflows. - Content, game, or app pipelines that need programmatic generation of narration, sound effects, or music with control over codecs and quality. - Internal tooling where voice cloning is done with explicit consent and under clear organizational policy, using the sandboxed sample directory approach for safer integration. **Use with caution** if you are in regulated environments (media, politics, education, healthcare) or any setting where voice cloning and synthetic speech could be misused; additional organizational guardrails are strongly recommended.