audio-transcribe

infquest/vibe-ops-plugin · updated Apr 8, 2026

MDX-style export adds YAML metadata + attribution linking explainx.ai and this canonical listing URL.

$npx skills add https://github.com/infquest/vibe-ops-plugin --skill audio-transcribe
0 commentsdiscussion
summary

使用 WhisperX 进行语音识别,支持多种语言和词级别时间戳对齐。

skill.md

Audio Transcriber

使用 WhisperX 进行语音识别,支持多种语言和词级别时间戳对齐。

Prerequisites

需要 Python 3.12(uv 会自动管理)。

Usage

When the user wants to transcribe audio/video: $ARGUMENTS

Instructions

你是一个语音转文字助手,使用 WhisperX 帮助用户将音频转换为文字。请按以下步骤操作:

Step 1: 获取输入文件

如果用户没有提供输入文件路径,询问他们提供一个。

支持的格式:

  • 音频:MP3, WAV, FLAC, M4A, OGG, etc.
  • 视频:MP4, MKV, MOV, AVI, etc.(会自动提取音频)

验证文件存在:

ls -la "$INPUT_FILE"

Step 2: 询问用户配置

⚠️ 必须:使用 AskUserQuestion 工具收集用户的偏好。不要跳过这一步。

使用 AskUserQuestion 工具收集以下信息:

  1. 模型大小:选择识别模型

    • 选项:
      • "base - 平衡速度和准确度 (Recommended)"
      • "tiny - 最快,准确度较低"
      • "small - 较快,准确度适中"
      • "medium - 较慢,准确度较高"
      • "large-v2 - 最慢,准确度最高"
  2. 语言:音频是什么语言?

    • 选项:
      • "自动检测 (Recommended)"
      • "中文 (zh)"
      • "英文 (en)"
      • "日文 (ja)"
      • "其他语言"
  3. 词级别对齐:是否需要词级别时间戳?

    • 选项:
      • "是 - 精确到每个词的时间 (Recommended)"
      • "否 - 只需要句子级别时间(更快)"
  4. 输出格式:输出什么格式?

    • 选项:
      • "TXT - 纯文本带时间戳 (Recommended)"
      • "SRT - 字幕格式"
      • "VTT - Web 字幕格式"
      • "JSON - 结构化数据(含词级别信息)"
  5. 输出路径:保存到哪里?

    • 建议默认:与输入文件同目录,文件名为 原文件名.txt(或对应格式)

Step 3: 执行转录脚本

使用 skill 目录下的 transcribe.py 脚本:

uv run /path/to/skills/audio-transcribe/transcribe.py "INPUT_FILE" [OPTIONS]

参数说明:

  • --model, -m: 模型大小 (tiny/base/small/medium/large-v2)
  • --language, -l: 语言代码 (en/zh/ja/...),不指定则自动检测
  • --no-align: 跳过词级别对齐
  • --no-vad: 禁用 VAD 过滤(如果转录有时间跳跃/遗漏,使用此选项)
  • --output, -o: 输出文件路径
  • --format, -f: 输出格式 (srt/vtt/txt/json)

示例:

# 基础转录(自动检测语言)
uv run skills/audio-transcribe/transcribe.py "video.mp4" -o "video.txt"

# 中文转录,输出 SRT 字幕
uv run skills/audio-transcribe/transcribe.py "audio.mp3" -l zh -f srt -o "subtitles.srt"

# 快速转录,不做词对齐
uv run skills/audio-transcribe/transcribe.py "audio.wav" --no-align -o "transcript.txt"

# 使用更大模型,输出 JSON(含词级别时间戳)
uv run skills/audio-transcribe/transcribe.py "speech.mp3" -m medium -f json -o "result.json"

# 禁用 VAD 过滤(解决时间跳跃/遗漏问题)
uv run skills/audio-transcribe/transcribe.py "audio.mp3" --no-vad -o "transcript.txt"

Step 4: 展示结果

转录完成后:

  1. 告诉用户输出文件的完整路径
  2. 显示部分转录内容预览
  3. 报告总时长和段落数

输出格式说明

TXT 格式

[00:00:00.000 - 00:00:03.500] 这是第一句话
[00:00:03.500 - 00:00:07.200] 这是第二句话

SRT 格式

1
00:00:00,000 --> 00:00:03,500
这是第一句话

2
00:00:03,500 --> 00:00:07,200
这是第二句话

JSON 格式(含词级别)

[
  {
    "start": 0.0,
    "end": 3.5,
    "text": "这是第一句话",
    "words": [
      {"word": "这是", "start": 0.0, "end": 0.5, "score": 0.95},
      ...
    ]
  }
]

常见问题处理

首次运行较慢

  • WhisperX 需要下载模型文件,首次运行会比较慢
  • 后续运行会使用缓存的模型

内存不足

  • 使用更小的模型(tiny 或 base)
  • 确保系统有足够的内存

识别准确度低

  • 尝试使用更大的模型(medium 或 large-v2)
  • 明确指定语言而不是自动检测

示例交互

用户:帮我把这个视频转成文字

助手:

  1. 检查 uv ✓
  2. 询问视频文件路径
  3. 使用 AskUserQuestion 询问模型、语言、格式等
  4. 执行转录
  5. 展示结果预览和保存路径

交互风格

  • 使用简单友好的语言
  • 解释不同模型大小的区别
  • 如果遇到错误,提供清晰的解决方案
  • 转录成功后给予积极反馈
how to use audio-transcribe

How to use audio-transcribe on Cursor

AI-first code editor with Composer

1

Prerequisites

Before installing skills in Cursor, ensure your development environment meets these requirements:

  • Cursor installed and configured on your development machine
  • Node.js version 16.0+ with npm package manager (verify with node --version)
  • Active project directory or workspace where you want to add audio-transcribe
2

Execute installation command

Execute the skills CLI command in your project's root directory to begin installation:

$npx skills add https://github.com/infquest/vibe-ops-plugin --skill audio-transcribe

The skills CLI fetches audio-transcribe from GitHub repository infquest/vibe-ops-plugin and configures it for Cursor.

3

Select Cursor when prompted

The CLI will show a list of available agents. Use arrow keys to navigate and space to select Cursor:

◆ Which agents do you want to install to?
│ ── Universal (.agents/skills) ── always included ────
│ • Amp
│ • Antigravity
│ • Cline
│ • Codex
│ ●Cursor(selected)
│ • Cursor
│ • Windsurf
4

Verify installation

Confirm successful installation by checking the skill directory location:

.cursor/skills/audio-transcribe

Reload or restart Cursor to activate audio-transcribe. Access the skill through slash commands (e.g., /audio-transcribe) or your agent's skill management interface.

Security & Verification Notice

We perform automated surface-level scans (Gen AI Scanner, Socket, Snyk) during installation. These checks detect common vulnerabilities but do not guarantee complete security. Always review skill source code and verify the publisher's reputation before production use.

Skills execute code in your development environment. Always verify the publisher's identity, review recent commits, and test in isolated environments before production deployment.

List & Monetize Your Skill

Submit your Claude Code skill and start earning

GET_STARTED →

Use Cases

User Story & Requirements Generation

Create detailed user stories, acceptance criteria, and feature specs

Example

Generate user stories for 'password reset feature' with acceptance criteria, edge cases, and test scenarios

Reduce spec writing time by 50%, ensure comprehensive coverage

Competitive Analysis

Research competitors, compare features, identify gaps

Example

Analyze 5 competitor products, create feature comparison matrix, suggest differentiation opportunities

Complete competitive research in 2 hours instead of 2 days

Roadmap Prioritization

Evaluate features using frameworks (RICE, ICE, Kano) and create prioritized backlogs

Example

Score 20 feature ideas using RICE framework, generate prioritized roadmap with rationale

Make data-driven prioritization decisions faster

Stakeholder Communication

Draft PRDs, status updates, and stakeholder presentations

Example

Create executive summary of Q3 roadmap, monthly progress report, feature launch announcement

Save 3-5 hours/week on communication overhead

Implementation Guide

Prerequisites

  • Claude Desktop or compatible AI client
  • Access to product documentation and roadmap tools (Jira, Notion, etc.)
  • Understanding of product management frameworks (RICE, Jobs-to-be-Done, etc.)
  • Stakeholder contact information and communication channels

Time Estimate

30-60 minutes to see productivity improvements

Installation Steps

  1. 1.Install product management skill
  2. 2.Start with user story generation for known feature
  3. 3.Progress to competitive analysis: research 2-3 competitors
  4. 4.Use for roadmap prioritization: apply RICE/ICE scoring
  5. 5.Draft stakeholder communications and refine based on feedback
  6. 6.Build template library for recurring PM tasks
  7. 7.Share effective prompts with product team

Common Pitfalls

  • Not validating competitive research—verify facts before sharing
  • Accepting user stories without involving engineering team
  • Over-relying on frameworks without qualitative judgment
  • Not customizing outputs to company culture and communication style
  • Skipping stakeholder validation of generated requirements

Best Practices

✓ Do

  • +Validate research and competitive analysis with real data
  • +Collaborate with engineering when generating technical requirements
  • +Customize frameworks and templates to your company context
  • +Use skill for first drafts, refine with stakeholder input
  • +Document successful prompt patterns for PM tasks
  • +Combine AI efficiency with human judgment and intuition

✗ Don't

  • Don't publish competitive analysis without fact-checking
  • Don't finalize user stories without engineering review
  • Don't make prioritization decisions solely on AI scoring
  • Don't skip customer validation of generated requirements
  • Don't ignore company-specific context and culture

💡 Pro Tips

  • Provide context: company goals, constraints, customer feedback
  • Ask for alternatives: 'Show 3 ways to prioritize this roadmap'
  • Request stakeholder-specific formatting: 'Executive summary vs. engineering spec'
  • Use skill for 70% generation + 30% customization to company needs

When to Use This

✓ Use When

Use for user story writing, competitive research, roadmap prioritization, stakeholder communication, and PRD drafting. Best for reducing repetitive documentation and research work.

✗ Avoid When

Avoid for strategic product vision (requires deep customer empathy), pricing decisions (needs market and financial expertise), or when face-to-face customer discovery is more valuable than speed.

Learning Path

  1. 1Basic: user stories, feature specs, status updates
  2. 2Intermediate: competitive analysis, prioritization frameworks, PRDs
  3. 3Advanced: product strategy, go-to-market planning, OKR setting
  4. 4Expert: product vision, market positioning, business model innovation

Discussion

Product Hunt–style comments (not star reviews)
  • No comments yet — start the thread.
general reviews

Ratings

4.628 reviews
  • Xiao Kim· Dec 28, 2024

    audio-transcribe reduced setup friction for our internal harness; good balance of opinion and flexibility.

  • Shikha Mishra· Dec 24, 2024

    Registry listing for audio-transcribe matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Kwame Flores· Dec 16, 2024

    Keeps context tight: audio-transcribe is the kind of skill you can hand to a new teammate without a long onboarding doc.

  • Henry Chawla· Dec 12, 2024

    I recommend audio-transcribe for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

  • Yash Thakker· Nov 15, 2024

    Solid pick for teams standardizing on skills: audio-transcribe is focused, and the summary matches what you get after install.

  • Hiroshi Mehta· Nov 7, 2024

    audio-transcribe has been reliable in day-to-day use. Documentation quality is above average for community skills.

  • Zara Ghosh· Nov 3, 2024

    Useful defaults in audio-transcribe — fewer surprises than typical one-off scripts, and it plays nicely with `npx skills` flows.

  • Sakura Ghosh· Oct 26, 2024

    audio-transcribe fits our agent workflows well — practical, well scoped, and easy to wire into existing repos.

  • Kwame Diallo· Oct 22, 2024

    Registry listing for audio-transcribe matched our evaluation — installs cleanly and behaves as described in the markdown.

  • Dhruvi Jain· Oct 6, 2024

    I recommend audio-transcribe for anyone iterating fast on agent tooling; clear intent and a small, reviewable surface area.

showing 1-10 of 28

1 / 3