一键在 Manus 中运行任何 Skill

开始使用

audio-transcriber

星标59

分支6

更新时间2026年2月28日 10:22

**Problem Category**: Audio file transcription using OpenAI Whisper

安装

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

在 Manus 中运行

来源

zzatpku

zzatpku/AgentFactory

打开 GitHub 仓库查看创作者相关仓库

下载

在 Manus 中运行

audio_transcriber

Description

Problem Category: Audio file transcription using OpenAI Whisper Applicable Questions: Transcribing audio files (mp3, wav, etc.) to text, especially Chinese audio Key Features:

Uses OpenAI Whisper model for transcription
Supports Chinese language transcription
Falls back to Google Speech Recognition if Whisper fails
Auto-installs required dependencies
Extracts file path from natural language query via LLM Skills Used: execute_shell_command Reasoning Pattern: 1) Parse query for file path 2) Verify file exists 3) Install whisper 4) Transcribe with whisper (base model, zh language) 5) Fallback to SpeechRecognition if needed 6) Return transcribed text Input Format: Natural language query containing an audio file path (e.g., 'Transcribe the audio file at /path/to/file.mp3') Output Format: {answer: transcribed text, summary: process description}

Skills Used

playwright, google_search, execute_shell_command

Usage

Entry file: audio_transcriber.py

Query type: Pass a focused sub-question as the query.

How to call:

<action>run_subagent</action>
<params>{"skill_name": "audio_transcriber", "query": "<your focused sub-question>"}</params>

同仓库更多 Skills

同仓库

create-subagent

zzatpku/AgentFactory

Create a new Python subagent file in the workspace. After creating, use run_subagent to test it (NOT use_saved_subagent).

2026-02-2859

finish

zzatpku/AgentFactory

Complete the task with a final answer and save reusable subagents as skills. Use this when you have successfully solved the question.

2026-02-2859

list-saved-subagents

zzatpku/AgentFactory

List all previously saved subagent skills. Use this to check if a suitable subagent already exists before creating a new one.

2026-02-2859

modify-subagent

zzatpku/AgentFactory

Edit an existing subagent file by replacing specific code snippets. Supports both workspace files and saved skills.

2026-02-2859

run-subagent

zzatpku/AgentFactory

Run a subagent - either a newly created one from workspace or a saved subagent from previous sessions.

2026-02-2859

view-subagent-code

zzatpku/AgentFactory

View the source code of a saved subagent skill. Use this to understand how an existing subagent works before reusing or adapting it.

2026-02-2859

name	audio_transcriber
description	Problem Category: Audio file transcription using OpenAI Whisper

audio_transcriber

Description

Problem Category: Audio file transcription using OpenAI Whisper Applicable Questions: Transcribing audio files (mp3, wav, etc.) to text, especially Chinese audio Key Features:

Uses OpenAI Whisper model for transcription
Supports Chinese language transcription
Falls back to Google Speech Recognition if Whisper fails
Auto-installs required dependencies
Extracts file path from natural language query via LLM Skills Used: execute_shell_command Reasoning Pattern: 1) Parse query for file path 2) Verify file exists 3) Install whisper 4) Transcribe with whisper (base model, zh language) 5) Fallback to SpeechRecognition if needed 6) Return transcribed text Input Format: Natural language query containing an audio file path (e.g., 'Transcribe the audio file at /path/to/file.mp3') Output Format: {answer: transcribed text, summary: process description}

Skills Used

playwright, google_search, execute_shell_command

Usage

Entry file: audio_transcriber.py

Query type: Pass a focused sub-question as the query.

How to call:

<action>run_subagent</action>
<params>{"skill_name": "audio_transcriber", "query": "<your focused sub-question>"}</params>