Communitygithub.com

YouTube 影片轉錄

使用 OpenAI Whisper 和 yt-dlp 將 YouTube 影片轉錄為文字。當使用者想要從 YouTube 影片獲取逐字稿、生成字幕、將影片語音轉換為文字、建立 SRT/VTT 字幕,或從 YouTube 網址提取口語內容時使用。

YouTube 影片轉錄 是什麼?

這項技能提供了一個完整的工作流程,將 YouTube 影片的音訊下載並使用 OpenAI 的 Whisper 模型進行語音轉文字轉錄。它支援多種輸出格式(txt、srt、vtt、json),並根據不同的準確度和速度需求提供多種模型大小(tiny 到 large)。使用者可以選擇使用指令列或 Python API 來進行轉錄,並可以指定語言以提高準確度。此技能適用於 Claude Code、Cursor、Codex 等支援執行指令與 Python 程式碼的 AI 代理平台,透過 yt-dlp 下載音訊、ffmpeg 處理格式、Whisper 進行轉錄,是一種高效且靈活的轉錄解決方案。

相容平台~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/TerminalSkills/skills/tree/HEAD/skills/youtube-transcription

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

YouTube 影片轉錄 是做什麼的?

使用 OpenAI Whisper 和 yt-dlp 將 YouTube 影片轉錄為文字。

概述

此技能使用 yt-dlp 從 YouTube 影片下載音訊,並使用 OpenAI 的 Whisper 模型進行轉錄。支援多種輸出格式(txt、srt、vtt、json)以及不同大小的模型,以達到不同的準確度/速度平衡。

指示

1. 安裝依賴項目

# 安裝 whisper 和 yt-dlp
pip install openai-whisper yt-dlp

# 確認 ffmpeg 已安裝(音訊處理需要)
ffmpeg -version

如果缺少 ffmpeg:

2. 從 YouTube 下載音訊

# 下載最佳音訊品質為 WAV 格式
yt-dlp -x --audio-format wav -o "%(title)s.%(ext)s" "YOUTUBE_URL"

# 下載為 MP3(檔案較小)
yt-dlp -x --audio-format mp3 -o "%(title)s.%(ext)s" "YOUTUBE_URL"

# 以影片 ID 作為檔名下載(避免特殊字元問題)
yt-dlp -x --audio-format wav -o "%(id)s.%(ext)s" "YOUTUBE_URL"

3. 選擇 Whisper 模型

模型參數量VRAM相對速度使用情境
tiny39M~1 GB~32x快速草稿、測試
base74M~1 GB~16x快速轉錄
small244M~2 GB~6x良好平衡
medium769M~5 GB~2x高準確度
large1550M~10 GB1x最佳準確度

僅限英文的模型(tiny.en、base.en、small.en、medium.en)對於英文內容速度更快。

4. 執行轉錄

指令列方式:

# 基本轉錄(自動偵測語言)
whisper audio.wav --model medium

# 指定語言以獲得更好的準確度
whisper audio.wav --model medium --language en

# 輸出特定格式
whisper audio.wav --model medium --output_format srt

# 一次輸出所有格式
whisper audio.wav --model medium --output_format all

# 指定輸出目錄
whisper audio.wav --model medium --output_dir ./transcripts

Python 方式:

import whisper

# 載入模型(首次執行時會下載)
model = whisper.load_model("medium")

# 轉錄
result = model.transcribe("audio.wav", language="en")

# 取得純文字
print(result["text"])

# 取得包含時間戳記的區段
for segment in result["segments"]:
    print(f"[{segment['start']:.2f} - {segment['end']:.2f}] {segment['text']}")

5. 單一指令管線

合併下載與轉錄:

# 一條指令完成下載和轉錄
yt-dlp -x --audio-format wav -o "audio.wav" "YOUTUBE_URL" && whisper audio.wav --model medium --output_format all

6. 替代方案:yt-whisper 工具

若要更簡單的工作流程,可以使用專用的 yt-whisper 套件:

# 安裝
pip install git+https://github.com/m1guelpf/yt-whisper.git

# 直接從網址轉錄
yt_whisper "https://www.youtube.com/watch?v=VIDEO_ID"

# 搭配選項
yt_whisper "YOUTUBE_URL" --model medium --language en --output_format srt

輸出格式

格式副檔名說明
txt.txt純文字逐字稿
srt.srtSubRip 字幕格式(包含時間戳記)
vtt.vttWebVTT 字幕格式
tsv.tsv以 Tab 分隔的值
json.json完整的資料,包含逐字時間戳記

範例

準則

  • 在知道口語語言時使用 --language 標記,可顯著提升準確度
  • 長影片(超過 1 小時)建議使用 small 或 medium 模型以平衡速度與準確度
  • 僅限英文的模型(.en 後綴)處理英文內容速度更快、準確度更高
  • 使用具備 CUDA 的 GPU 可大幅加速轉錄;CPU 也可用,但速度慢 5-10 倍
  • 若轉錄失敗,請確認 ffmpeg 已正確安裝且在 PATH 環境變數中
  • 含有背景音樂的影片,較大的模型(medium/large)處理效果較佳
  • 轉錄完成後請清理音訊檔案以節省磁碟空間
  • 使用 --output_format all 一次取得所有格式,再從中挑選所需格式

Individual skills in this repo

This repo contains 20 individual skills — each has its own dedicated page.

TerminalSkills/skills

>- Run GitHub Actions locally with act. Use when a user asks to test GitHub Actions workflows locally, debug CI pipelines without pushing, or run workflows offline.

TerminalSkills/skills

>- You are an expert in AG2 (formerly AutoGen), the open-source multi-agent conversation framework. You help developers build systems where multiple AI agents collaborate through structured conversations — with tool use, human-in-the-loop, code execution, group chat orchestration, and nested conversations — for complex tasks like software development, research, and data analysis.

TerminalSkills/skills

>- Generate short-form videos with AI — script writing, text-to-speech narration, stock footage selection, subtitle generation, and video assembly. Use when: creating TikTok/YouTube Shorts/Reels content, automating video production, building content pipelines.

TerminalSkills/skills

>- Animate 3D objects and characters in Blender with Python. Use when the user wants to keyframe properties, create armatures and rigs, set up IK/FK chains, animate shape keys for facial animation, edit F-Curves, use the NLA editor to blend actions, add drivers for expression-based animation, or script any animation workflow in Blender.

TerminalSkills/skills

>- Automate motion capture and tracking workflows in Blender with Python. Use when the user wants to import BVH or FBX mocap data, retarget motion to armatures, track camera or object motion from video, solve camera motion, clean up motion capture data, or script any tracking pipeline in Blender.

TerminalSkills/skills

>- You are an expert in Bolt.new by StackBlitz, the AI-powered full-stack development environment that runs entirely in the browser. You help developers go from idea to deployed app in minutes using natural language prompts — Bolt generates complete applications with frontend, backend, database, and deployment, all running in a WebContainer without local setup.

TerminalSkills/skills

>- Assists with using Bun as an all-in-one JavaScript/TypeScript runtime, package manager, bundler, and test runner. Use when building HTTP servers, managing packages, running tests, or migrating from Node.js. Trigger words: bun, bun serve, bun install, bun test, bun build, javascript runtime, bun runtime.

TerminalSkills/skills

>- Self-host customer support with Chatwoot. Use when a user asks to set up open-source customer support, add live chat without SaaS costs, build a multi-channel inbox, or deploy a free Intercom alternative.

TerminalSkills/skills

>- You are an expert in Chi, the lightweight, idiomatic Go HTTP router built on `net/http`. You help developers build composable HTTP services using Chi's middleware stack, route groups, URL parameters, sub-routers, and context-based request scoping — providing Express-like ergonomics while staying 100% compatible with Go's standard library.

TerminalSkills/skills

When the user wants to edit, review, or improve existing marketing copy. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' or 'copy sweep.' This skill provides a systematic approach to editing marketing copy through multiple focused passes.

TerminalSkills/skills

>- Add live chat and customer support with Crisp. Use when a user asks to add a chat widget, implement live customer support, set up a help desk, create a knowledge base, or add a chatbot to a website.

TerminalSkills/skills

>- Assists with building custom interactive data visualizations using D3.js. Use when creating charts, graphs, maps, force layouts, or hierarchical diagrams that require fine-grained control beyond what charting libraries provide. Trigger words: d3, data visualization, chart, svg, scales, force graph, treemap, choropleth.

TerminalSkills/skills

dbt (data build tool) transforms data in your warehouse using SQL SELECT statements. Learn project setup, models, tests, documentation, incremental materializations, and integration with data warehouses like PostgreSQL, BigQuery, and Snowflake.

TerminalSkills/skills

>- You are an expert in dlt, the open-source Python library for building data pipelines. You help developers load data from any API, file, or database into warehouses and lakes using simple Python decorators — with automatic schema inference, incremental loading, and built-in data contracts. dlt is the "requests library for data pipelines.

TerminalSkills/skills

Data Version Control for ML projects. Track large datasets and models alongside Git, build reproducible ML pipelines, and run experiments with metric comparison. Works with any storage backend including S3, GCS, Azure, and local filesystems.

TerminalSkills/skills

>- You are an expert in E2B, the cloud platform for running AI-generated code in secure sandboxes. You help developers give AI agents the ability to execute code, install packages, read/write files, and run long processes in isolated cloud environments — each sandbox is a lightweight VM that boots in ~150ms with full Linux, filesystem, and networking.

TerminalSkills/skills

>- Transcode, convert, edit, and process audio and video with FFmpeg. Use when a user asks to convert video formats (webm to mp4, mkv to mp4), extract audio from video, compress video files, trim or cut clips, concatenate videos, add subtitles, create thumbnails, apply filters, change resolution or bitrate, re-encode media, create GIFs from video, add watermarks, normalize audio, stream media, or build automated media processing pipelines.

TerminalSkills/skills

>- Create advanced animations with GSAP. Use when building complex timelines, scroll-driven animations, SVG morphing, text animations, or high-performance web animations beyond CSS capabilities.

TerminalSkills/skills

>- Generate deterministic MP4 videos from HTML, CSS, media, and seekable animations using HeyGen's HyperFrames framework. Use when someone asks to "render HTML to video", "make a video with HyperFrames", "create a programmatic video", "turn an animation into MP4", "build a launch/product video from HTML", "render GSAP/Lottie/Three.js to video", or set up an agent-driven video pipeline. Covers init/preview/render/add/lint/inspect commands, data-* timing attributes, animation adapters, and the component catalog.

TerminalSkills/skills

When the user wants to perform load testing, stress testing, or performance testing of APIs and websites using k6. Also use when the user mentions "k6," "load test," "performance test," "stress test," "spike test," "soak test," "thresholds," "virtual users," or "VUs." For browser-based testing, see selenium.

相關技能