← Back to Skills Marketplace
ElevenLabs Speech-to-Text
by
clawdbotborges
· GitHub ↗
· v1.0.0
4818
Downloads
6
Stars
14
Active Installs
1
Versions
Install in OpenClaw
/install elevenlabs-stt
Description
Transcribe audio files using ElevenLabs Speech-to-Text (Scribe v2).
Usage Guidance
Install this only if you are comfortable sending the audio files you choose to ElevenLabs and using your ElevenLabs API key for that processing. Avoid submitting confidential, regulated, or consent-sensitive recordings unless your use of ElevenLabs is approved, and ensure jq is installed because the script depends on it.
Capability Analysis
Type: OpenClaw Skill
Name: elevenlabs-stt
Version: 1.0.0
The skill bundle is a legitimate wrapper for the ElevenLabs Speech-to-Text API. The `scripts/transcribe.sh` script uses `curl` to send audio files to the official `https://api.elevenlabs.io/v1/speech-to-text` endpoint, using an API key provided via the `ELEVENLABS_API_KEY` environment variable. There is no evidence of data exfiltration to unauthorized endpoints, malicious execution, persistence mechanisms, obfuscation, or prompt injection attempts against the agent in any of the files (`_meta.json`, `SKILL.md`, `scripts/transcribe.sh`, `README.md`). The use of `curl` and `jq` is declared and necessary for the skill's stated purpose.
Capability Assessment
Purpose & Capability
The skill's capability matches its stated purpose: it transcribes user-selected audio through ElevenLabs Speech-to-Text using the official API endpoint.
Instruction Scope
Instructions are user-directed and limited to running a transcription script on a chosen file with optional flags; there is no background execution, bulk file scanning, or destructive behavior.
Install Mechanism
Installation is conventional and requires an ElevenLabs API key; the script also uses jq even though only curl is declared in the skill metadata.
Credentials
Network access and ELEVENLABS_API_KEY are proportionate for a cloud speech-to-text integration, but audio content and API-key-backed usage are sensitive considerations.
Persistence & Privilege
No persistence, privilege escalation, credential-store access, hidden writes, or long-running workers are present in the inspected artifacts.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install elevenlabs-stt - After installation, invoke the skill by name or use
/elevenlabs-stt - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of elevenlabs-stt skill.
- Transcribe audio files using ElevenLabs Scribe v2 model.
- Supports 90+ languages and speaker diarization.
- Multiple output options: plain text, JSON with timestamps, audio event tagging.
- Works with all major audio and video formats.
- Requires ELEVENLABS_API_KEY for authentication.
Metadata
Frequently Asked Questions
What is ElevenLabs Speech-to-Text?
Transcribe audio files using ElevenLabs Speech-to-Text (Scribe v2). It is an AI Agent Skill for Claude Code / OpenClaw, with 4818 downloads so far.
How do I install ElevenLabs Speech-to-Text?
Run "/install elevenlabs-stt" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is ElevenLabs Speech-to-Text free?
Yes, ElevenLabs Speech-to-Text is completely free (open-source). You can download, install and use it at no cost.
Which platforms does ElevenLabs Speech-to-Text support?
ElevenLabs Speech-to-Text is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created ElevenLabs Speech-to-Text?
It is built and maintained by clawdbotborges (@clawdbotborges); the current version is v1.0.0.
More Skills