← Back to Skills Marketplace
889
Downloads
0
Stars
4
Active Installs
3
Versions
Install in OpenClaw
/install zhipu-asr
Description
Automatic Speech Recognition (ASR) using Zhipu AI (BigModel) GLM-ASR model. Use when you need to transcribe audio files to text. Supports Chinese audio trans...
Usage Guidance
This skill appears to do exactly what it says: convert audio locally (ffmpeg) and upload it to Zhipu's transcription API using ZHIPU_API_KEY. Before installing, confirm you trust the destination (open.bigmodel.cn) and are comfortable sending audio (which may contain sensitive PII) to that external service. Ensure ffmpeg/curl/jq are installed from trusted package sources. Note the small metadata inconsistencies (package.json/_meta.json versions and declared required bins) — these look like packaging oversights but you may want to verify the packaged files match the registry metadata and the published version if that matters to you.
Capability Analysis
Type: OpenClaw Skill
Name: zhipu-asr
Version: 1.0.2
The skill is a legitimate wrapper for the Zhipu AI Automatic Speech Recognition (ASR) service. The core script, `scripts/speech_to_text.sh`, performs standard audio processing using ffmpeg and transmits data to the official Zhipu AI API endpoint (open.bigmodel.cn). It includes proper input validation for file size and duration, uses secure temporary file handling, and lacks any indicators of data exfiltration, malicious execution, or prompt injection.
Capability Assessment
Purpose & Capability
The name/description, SKILL.md, and the included shell script all align with an ASR transcription skill. The only minor inconsistency is metadata in package.json/_meta.json (and package.json lists only jq in openclaw.requires while the script also requires curl and ffmpeg); this looks like sloppy packaging rather than malicious behavior.
Instruction Scope
Runtime instructions and the script stay within scope: they read the provided audio file, optionally convert it with ffmpeg, check size/duration, and POST the file and optional context/hotwords to the declared Zhipu API endpoint. The script does not read other environment variables, system files, or contact unexpected endpoints.
Install Mechanism
There is no install spec (instruction-only with a shipped shell script). That is low-risk; no external archives or binaries are downloaded by the skill itself. The script requires standard system tools (jq, curl, ffmpeg) already expected for this functionality.
Credentials
Only ZHIPU_API_KEY is requested, which is proportionate to uploading audio to Zhipu's API. No other secrets or unrelated credentials are required or referenced.
Persistence & Privilege
always is false and the skill does not attempt to modify other skills or system settings. It does not request persistent elevated presence beyond normal user invocation.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install zhipu-asr - After installation, invoke the skill by name or use
/zhipu-asr - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.2
Added curl and ffmpeg to requirements; added 30s duration check; improved script cleanup and silent transcoding.
v1.0.1
Initial release: Automatic Speech Recognition using Zhipu AI GLM-ASR model with Chinese language support, context prompts, and hotwords
v1.0.0
Initial release: Automatic Speech Recognition using Zhipu AI GLM-ASR model with Chinese language support, context prompts, and hotwords
Metadata
Frequently Asked Questions
What is Zhipu Asr?
Automatic Speech Recognition (ASR) using Zhipu AI (BigModel) GLM-ASR model. Use when you need to transcribe audio files to text. Supports Chinese audio trans... It is an AI Agent Skill for Claude Code / OpenClaw, with 889 downloads so far.
How do I install Zhipu Asr?
Run "/install zhipu-asr" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Zhipu Asr free?
Yes, Zhipu Asr is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Zhipu Asr support?
Zhipu Asr is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Zhipu Asr?
It is built and maintained by xiaofei (@franklu0819-lang); the current version is v1.0.2.
More Skills