← Back to Skills Marketplace
118
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install fun-asr-nano
Description
Fun-ASR-Nano 基于 sherpa-onnx 引擎的本地语音识别，完全离线运行。当用户需要转录音频文件时触发。
README (SKILL.md)
Fun-ASR-Nano
Fun-ASR-Nano 基于 sherpa-onnx 引擎的本地语音识别，完全离线运行，无需网络连接。支持多种语言和方言的语音转文字。
中文包括 7 种方言（吴语、粤语、闽语、客家话、赣语、湘语、晋语）和 26 种地方口音（河南、山西、湖北、四川、重庆、云南、贵州、广东、广西 及其他 20 多个地区）。
英文和日文涵盖多种地方口音。
此外还支持歌词识别和说唱语音识别。
特点：
- 本地运行，保护隐私
- 离线识别，无需网络
- 支持多种音频格式
激活条件
| 触发场景 | 说明 |
|---|---|
| 用户发送音频文件 | .wav / .mp3 / .m4a / .flac / .ogg 等格式 |
| 用户要求转录 | "转写音频"、"语音转文字" |
| 音频文件处理 | 需要提取音频中的文字内容 |
使用方法
安装依赖
pip install sherpa-onnx soundfile modelscope
转写音频文件
python scripts/cli.py audio.wav
版本：1.0.0 创建于：2026-03-18
Usage Guidance
This skill appears to implement local ASR, but it is misleading to call it 'completely offline' because the provided script uses modelscope.snapshot_download to fetch model weights at runtime. Before installing: (1) expect network access to download model files and Python packages; (2) confirm you are comfortable downloading and storing third-party model weights (check license and trustworthiness of the 'pengzhendong/Fun-ASR-Nano-int8' model on ModelScope); (3) consider running the script in an isolated environment (VM/container) if you want to limit exposure; (4) if you truly need offline operation without any network access, verify you already have the required model folder locally and modify the script to avoid snapshot_download; (5) be aware that while the script does not transmit audio, downloading models involves network activity and writing files to disk — review downloaded files and their origins.
Capability Analysis
Type: OpenClaw Skill
Name: fun-asr-nano
Version: 1.0.0
The skill bundle provides legitimate local speech-to-text functionality using the sherpa-onnx engine and Fun-ASR-Nano models. The script `scripts/cli.py` uses the standard `modelscope` library to download model weights and performs offline inference as described in `SKILL.md`. No indicators of data exfiltration, malicious execution, or harmful prompt injection were found.
Capability Assessment
Purpose & Capability
The declared purpose (local/offline speech recognition using sherpa-onnx) matches the included code and CLI. However, the skill's claim of '完全离线运行' (completely offline) conflicts with the code that downloads model artifacts from ModelScope at runtime (snapshot_download).
Instruction Scope
SKILL.md omits mention that the script will fetch model files from a remote registry. The runtime instructions tell the user to pip install dependencies but do not explain the need for network access or where models will be fetched from. The CLI reads local audio files only (no direct exfiltration), but it will initiate network activity to download model snapshots.
Install Mechanism
There is no formal install spec (instruction-only). The documentation asks users to pip install packages (normal), but the script uses modelscope.snapshot_download which will download model archives from ModelScope and write them to disk. The download source is an external model registry (ModelScope) rather than a bundled local model; this is higher-risk than a fully offline bundle but not itself malicious.
Credentials
The skill requests no environment variables, credentials, or privileged config paths. There are no apparent demands for unrelated secrets or system credentials.
Persistence & Privilege
Flags show normal invocation (not always:true). The skill does not request permanent platform presence or attempt to modify other skills' configurations. It will download and store model files locally using modelscope, which is expected for model-heavy tools.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install fun-asr-nano - After installation, invoke the skill by name or use
/fun-asr-nano - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of Fun-ASR-Nano (version 1.0.0).
- Provides fully offline, local speech-to-text based on the sherpa-onnx engine.
- Supports recognition for seven major Chinese dialects, 26 regional accents, as well as English and Japanese with multiple accents.
- Handles various audio formats such as .wav, .mp3, .m4a, .flac, and .ogg.
- Includes specialized support for lyrics and rap speech recognition.
- Focused on privacy by running entirely offline without requiring any network connection.
Metadata
Frequently Asked Questions
What is Local fun-asr-nano powered by sherpa-onnx?
Fun-ASR-Nano 基于 sherpa-onnx 引擎的本地语音识别，完全离线运行。当用户需要转录音频文件时触发。 It is an AI Agent Skill for Claude Code / OpenClaw, with 118 downloads so far.
How do I install Local fun-asr-nano powered by sherpa-onnx?
Run "/install fun-asr-nano" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Local fun-asr-nano powered by sherpa-onnx free?
Yes, Local fun-asr-nano powered by sherpa-onnx is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Local fun-asr-nano powered by sherpa-onnx support?
Local fun-asr-nano powered by sherpa-onnx is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Local fun-asr-nano powered by sherpa-onnx?
It is built and maintained by 彭震东 (@pengzhendong); the current version is v1.0.0.
More Skills