← Back to Skills Marketplace
asr
by
ModestyRichards
· GitHub ↗
· v1.0.2
· MIT-0
125
Downloads
0
Stars
0
Active Installs
2
Versions
Install in OpenClaw
/install modesty-asr
Description
Fast, accurate automatic speech-to-text transcription supporting 100 languages from URLs or local files via SkillBoss API Hub.
Usage Guidance
This skill implements a straightforward ASR client that uploads audio to SkillBoss and needs a SKILLBOSS_API_KEY. Before installing: (1) Confirm you trust https://skillboss.co and review its privacy policy because your audio will be sent there; (2) set the SKILLBOSS_API_KEY only if you intend to allow audio uploads; (3) be cautious when transcribing local files that may contain sensitive information; (4) note the minor packaging mismatch (registry metadata vs. manifest) — expect to provide the SKILLBOSS_API_KEY despite the top-level summary saying "none"; and (5) if you need offline/local-only transcription, this skill is not suitable because it depends on an external API.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description, SKILL.md, manifest.json, and scripts/asr.sh all consistently implement an ASR client that sends base64-encoded audio to SkillBoss API (https://api.skillboss.co/v1/pilot). The required capability (an API key) is what you'd expect for this purpose.
Instruction Scope
Runtime instructions and the script only perform: download a URL or read a user-supplied local file, base64-encode it, and POST JSON to the SkillBoss endpoint. This is coherent for transcription, but it does transmit user audio (which may be sensitive) to an external service—users should be aware and consent to that.
Install Mechanism
No install spec or remote downloads; this is instruction-only with a bundled shell script. Nothing is fetched from arbitrary URLs or written beyond temporary files in /tmp. Risk from install mechanism is low.
Credentials
The skill uses a single API credential (SKILLBOSS_API_KEY) which is proportionate to the stated purpose. However, the registry metadata at the top of the report said "Required env vars: none" while manifest.json and SKILL.md both declare SKILLBOSS_API_KEY—this mismatch is likely a packaging/manifest oversight and should be corrected.
Persistence & Privilege
The skill is not always-enabled, does not modify other skills or system-wide config, and does not request elevated or persistent system privileges. It writes transient temp files and removes them; it does not store credentials on disk.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install modesty-asr - After installation, invoke the skill by name or use
/modesty-asr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
- Updated all references from heybossai.com to skillboss.co in SKILL.md.
- No functional or code changes; documentation only.
- Ensured setup instructions direct users to the current API provider site.
v1.0.0
- Initial release of the ASR (Automatic Speech Recognition) skill.
- Transcribe audio from both URLs and local files into text using SkillBoss API Hub.
- Supports 100+ languages with automatic detection and optional language hints.
- Easy integration: configure via the SKILLBOSS_API_KEY environment variable.
- Designed for high-volume, agent-based, or automated pipelines.
- Returns transcription as structured JSON in `.result.text`; clear error if API key missing.
Metadata
Frequently Asked Questions
What is asr?
Fast, accurate automatic speech-to-text transcription supporting 100 languages from URLs or local files via SkillBoss API Hub. It is an AI Agent Skill for Claude Code / OpenClaw, with 125 downloads so far.
How do I install asr?
Run "/install modesty-asr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is asr free?
Yes, asr is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does asr support?
asr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created asr?
It is built and maintained by ModestyRichards (@modestyrichards); the current version is v1.0.2.
More Skills