← Back to Skills Marketplace
292
Downloads
0
Stars
0
Active Installs
3
Versions
Install in OpenClaw
/install qwen-asr-local
Description
Local speech-to-text using Qwen3-ASR (CPU-only, no API key, no cloud). Use when: (1) a voice message or audio file needs transcription, (2) user asks to tran...
Usage Guidance
This skill appears consistent with its stated purpose. Before installing: (1) review the install script and the GitHub release it downloads from and only run it if you trust that repo (prebuilt native binaries execute with your user privileges); (2) expect ~1.5 GB model download and network access to GitHub/HuggingFace; (3) ffmpeg is required for non‑WAV inputs; (4) install writes to ~/.local/bin and ~/.openclaw/tools/qwen-asr — you may need to add ~/.local/bin to your PATH; (5) if you need fully air-gapped/local operation, verify the model is cached locally or that the model download will not require a HuggingFace token. Otherwise the skill is internally coherent and proportionate.
Capability Analysis
Type: OpenClaw Skill
Name: qwen-asr-local
Version: 0.1.2
The skill provides local speech-to-text by downloading a pre-compiled binary from a third-party GitHub repository (huanglizhuo/QwenASR) and a 1.5GB model from HuggingFace. While these actions are aligned with the stated purpose of the tool, downloading and executing unverified binaries from external sources is a high-risk capability. The scripts (install.sh and transcribe.sh) are functionally sound and do not show signs of intentional malice, data exfiltration, or prompt injection.
Capability Assessment
Purpose & Capability
Name/description (local Qwen3-ASR CPU transcription) match the declared requirement (qwen-asr binary) and the included scripts. No unrelated environment variables, credentials, or unusual binaries are requested.
Instruction Scope
SKILL.md and transcribe.sh only describe running the qwen-asr binary (locally) and converting audio via ffmpeg when needed. The install script downloads a release and the model and writes them under the user's home; scripts do not read unrelated system files or exfiltrate data. The only optional env var is QWEN_ASR_MODEL_DIR to override the model path.
Install Mechanism
Install script fetches a prebuilt release from the project's GitHub Releases and extracts it to ~/.local/bin; model download is performed by qwen-asr (presumably fetching from HuggingFace). Using GitHub Releases and the model download command is expected for this purpose; no obscure/shortened URLs or third-party personal servers are used.
Credentials
No secrets or extra environment variables are required. The only environment interaction is an optional QWEN_ASR_MODEL_DIR and use of PATH/ffmpeg. Note: model download requires network access and some HuggingFace-hosted models may require authentication in other contexts, but no credential is requested by this skill.
Persistence & Privilege
Skill is not forcible (always:false) and does not modify other skills or system-wide agent settings. It writes binaries/models into the user's home directories (standard for local tools) but does not request elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qwen-asr-local - After installation, invoke the skill by name or use
/qwen-asr-local - Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
- Added source code and original implementation links for QwenASR and qwen-asr in documentation.
- No changes to functionality or usage.
v0.1.1
- Added support for automatic audio format conversion via ffmpeg when using the transcribe.sh script.
- Now accepts a wider range of audio formats (wav, mp3, m4a, ogg, flac, opus, webm, aac, etc.) for transcription.
- Clarified that direct qwen-asr command works with WAV files only.
- Updated usage instructions to reflect these changes.
v0.1.0
Initial release of qwen-asr-local: local, offline speech-to-text using Qwen3-ASR.
- Runs entirely on CPU with no API key or cloud required.
- Supports transcription of audio files, voice messages, and input from stdin.
- Provides segmented and real-time streaming transcription modes.
- Compatible with macOS and Linux only.
- Simple installation via provided script; downloads pre-built binary and model files.
Metadata
Frequently Asked Questions
What is Qwen ASR?
Local speech-to-text using Qwen3-ASR (CPU-only, no API key, no cloud). Use when: (1) a voice message or audio file needs transcription, (2) user asks to tran... It is an AI Agent Skill for Claude Code / OpenClaw, with 292 downloads so far.
How do I install Qwen ASR?
Run "/install qwen-asr-local" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Qwen ASR free?
Yes, Qwen ASR is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Qwen ASR support?
Qwen ASR is cross-platform and runs anywhere OpenClaw / Claude Code is available (darwin, linux).
Who created Qwen ASR?
It is built and maintained by lizhuo (@huanglizhuo); the current version is v0.1.2.
More Skills