sensevoice-local

Transcribe Chinese-heavy classroom recordings locally using SenseVoice wrapper scripts.

Updated Mar 8, 2026
One-click install
npx skills add https://github.com/zhuchenyu2008/skills --skill sensevoice-local
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: sensevoice-local
Source: https://github.com/zhuchenyu2008/skills/tree/main/sensevoice-local
Command: npx skills add https://github.com/zhuchenyu2008/skills --skill sensevoice-local

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Local classroom audio transcripts are often private, large, or restricted by cloud services; this skill provides a local, CPU-based transcription workflow to convert class recordings into text without exporting data.

Core Features & Use Cases

  • Local transcription of classroom recordings on your own machine for privacy and control.
  • One-shot upload page: start a temporary web interface to upload large audio files when chat channels are unsuitable for large payloads.
  • Deterministic wrappers and runtime isolation: use the provided scripts to invoke SenseVoice without manual docker commands or unsafe ad-hoc setups.

Quick Start

Run the transcription by calling the transcribe_file.sh script with your audio path.

Frequently Asked Questions about sensevoice-local

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe Chinese classroom recordings locally for privacy?

You can transcribe Chinese-heavy classroom recordings locally by running the provided transcribe_file.sh wrapper script with your audio path to invoke SenseVoice on your own CPU-based server without exporting data.

What is the best way to upload large audio files for transcription when chat platforms restrict size?

To upload large audio files for transcription when messaging platforms restrict size, you can start the on-demand one-shot upload page, which provides a temporary web interface to securely receive your large payloads.

Can I run offline speech recognition on a local server without cloud services?

Yes, you can run offline speech recognition on a local server using SenseVoice. The skill provides deterministic wrappers and runtime isolation to execute the transcription process entirely offline without relying on external cloud services.

Do I need Docker to run local ASR transcription with SenseVoice?

You do not need to manually run Docker commands for local ASR transcription. The skill provides wrapper scripts that handle the invocation of SenseVoice automatically, ensuring a safe and reliable setup without ad-hoc manual configurations.

What should I do if my local audio transcription script is not working in an OpenClaw environment?

If your local audio transcription script is not working in an OpenClaw environment, consult the included troubleshooting references designed to ensure reliable operation and resolve common runtime or configuration issues.

Does SenseVoice local transcription support CPU-based processing for classroom audio?

Yes, SenseVoice local transcription supports CPU-based processing for classroom audio. This allows you to convert class recordings into text entirely on your own machine, ensuring maximum privacy and control over sensitive educational data.