YouTube Transcript Fetcher (YTT)
YouTube 字幕获取器
使用 Whisper AI 转录功能从任何 YouTube 视频中获取字幕。搜索 YouTube 并获取搜索结果前几名的字幕。无需 YouTube API 密钥。
功能特性
Whisper 驱动 — 最先进的 AI 转录,准确率 99% 以上
YouTube 搜索 — 搜索 YouTube 并获取搜索结果前几名的字幕
无需 API 密钥 — 无需 YouTube Data API 凭据即可工作
多种格式 — 支持文本、JSON、SRT、VTT 输出
缓存机制 — 基于 SQLite 的缓存,避免重复转录
无速率限制 — Whisper 在本地运行,无外部 API 限制
CLI 与库 — 可作为命令行工具或 Python 模块使用
MCP 服务器 — 通过模型上下文协议 (MCP) 与 AI 工具集成
安装
# Clone the repository
git clone https://github.com/andrewctf/ytt.git
cd ytt
# Create virtual environment
python -m venv .venv
source .venv/bin/activate # Linux/Mac
.venv\Scripts\activate # Windows
# Install dependencies
pip install -r requirements.txt
# Optional: GPU support
pip install torch torchvision --index-url https://download.pytorch.org/whl/cu128注意: 有关详细的 GPU/CUDA 设置,请参阅 QUICKSTART.md。
Whisper 的额外设置
Whisper 需要 ffmpeg 进行音频提取:
Windows (使用 winget):
winget install ffmpegmacOS:
brew install ffmpegLinux:
sudo apt install ffmpeg快速入门
有关详细的安装和设置说明,请参阅 QUICKSTART.md。
CLI
# Get transcript (Whisper is used by default)
python cli.py transcript VIDEO_ID
# Or with a full YouTube URL
python cli.py transcript "https://www.youtube.com/watch?v=a1JTPFfshI0"
# Different output formats
python cli.py transcript VIDEO_ID --format json
python cli.py transcript VIDEO_ID --format srt
python cli.py transcript VIDEO_ID --format vtt
# Save to file
python cli.py transcript VIDEO_ID --output transcript.txt
# Batch processing
python cli.py transcript VIDEO_ID1 VIDEO_ID2 VIDEO_ID3
# Search YouTube for videos and get transcripts
python cli.py search "Python tutorial" --limit 5 --with-transcripts
# Search only (no transcripts)
python cli.py search "Python tutorial" --limit 10
# JSON output for search
python cli.py search "Python tutorial" --format json
# Cache management
python cli.py cache-stats
python cli.py cache-stats --clean # Remove expired entriesPython 库
from src.service import get_transcript
from src.search_service import search, search_and_get_transcripts
# Basic usage
result = await get_transcript("VIDEO_ID")
print(result.content)
# With options
result = await get_transcript(
"VIDEO_ID",
language="en",
output_format="json",
use_cache=True,
)
# Access metadata
print(f"Source: {result.source}") # 'whisper' or 'innertube'
print(f"Language: {result.language}") # Detected language
print(f"Video ID: {result.video_id}")
# Search YouTube for videos
results = await search("Python tutorial", max_results=5)
for video in results:
print(f"{video.title} ({video.video_id}) - {video.channel_name}")
# Search and get transcripts for results
results = await search_and_get_transcripts("Python tutorial", max_results=3, language="en")
for video, transcript in results:
if transcript:
print(f"{video.title}: {transcript.content[:100]}...")同步使用方式:
import asyncio
from src.service import get_transcript
from src.search_service import search
def fetch_transcript(video_id):
return asyncio.run(get_transcript(video_id))
def search_videos(query, max_results=5):
return asyncio.run(search(query, max_results=max_results))
result = fetch_transcript("VIDEO_ID")
print(result.content)
videos = search_videos("Python tutorial")MCP 服务器
注意: 有关 Claude Desktop、Cursor 和 VS Code 的详细配置,请参阅 QUICKSTART.md。
启动 MCP 服务器:
python -m mcp_server.server该服务器公开了三个工具:
get_transcript- 获取单个视频的字幕get_transcripts_batch- 并发获取多个视频的字幕search_videos- 在 YouTube 上搜索匹配查询的视频
或者通过添加到 MCP 设置中与 Claude Desktop 集成:
{
"mcpServers": {
"yt-transcript": {
"command": "python",
"args": ["-m", "mcp_server.server"],
"cwd": "/absolute/path/to/ytt"
}
}
}工作原理
Video ID → Cache Check
↓ found?
Return Cached
↓ not found
Whisper (primary)
- Download audio via yt-dlp
- Transcribe with faster-whisper
- Returns word-level timestamps
↓ fails?
Innertube API (fallback)
- Extract API key from video page
- Fetch caption tracks
- Parse JSON3 timed text
↓
Cache Result
↓
Format & ReturnWhisper (主要方式)
使用
yt-dlp下载音频使用
faster-whisper(CPU 优化版) 进行转录返回逐词时间戳和片段文本
适用于任何有音频的视频
处理速度约为实时速度的 1-3 倍
Innertube API (回退方式)
抓取 YouTube 内部 API
无需 API 密钥
速度快 (每个视频约 0.5-2 秒)
覆盖率约 85% (部分视频缺少字幕)
有速率限制 (每个 IP 约 5 次请求/10 秒)
输出格式
文本 (默认)
Good morning, here we are, a live suturing course like nobody else has ever
done and what are we covering, we're covering every suturing technique...JSON
{
"video_id": "a1JTPFfshI0",
"language": "en",
"source": "whisper",
"segments": [
{"start": 0.0, "end": 4.5, "text": "Good morning, here we are..."},
{"start": 4.5, "end": 9.2, "text": "a live suturing course..."}
]
}SRT (SubRip)
1
00:00:00,000 --> 00:00:04,500
Good morning, here we are, a live suturing course...
2
00:00:04,500 --> 00:00:09,200
a live suturing course like nobody else...VTT (WebVTT)
WEBVTT
00:00:00.000 --> 00:00:04.500
Good morning, here we are, a live suturing course...
00:00:04.500 --> 00:00:09.200
a live suturing course like nobody else...配置
编辑 config.py 以自定义行为:
class Config:
# Whisper settings
WHISPER_MODEL = "base" # tiny/base/small/medium/large
WHISPER_FALLBACK_ENABLED = True
# Cache settings
CACHE_TTL_DAYS = 7
CACHE_DB_PATH = ".transcript_cache.db"
# Rate limiting (for Innertube fallback)
RATE_LIMIT_RATE = 0.5 # tokens per second
RATE_LIMIT_BURST = 5 # max bucket size
# Batch processing
MAX_BATCH_SIZE = 50Whisper 模型
模型 | 速度 | 准确率 | 内存 |
tiny | 10x | ~75% | ~1GB |
base | 7x | ~85% | ~1GB |
small | 4x | ~90% | ~2GB |
medium | 2x | ~95% | ~5GB |
large | 1x | ~97% | ~6GB |
对于大多数用例,推荐使用 base 模型——速度快且足够准确。
文件结构
ytt/
├── src/
│ ├── __init__.py
│ ├── fetcher.py # Innertube API client
│ ├── whisper_runner.py # Whisper transcription
│ ├── parser.py # Caption parsing utilities
│ ├── formatters.py # Output formatters
│ ├── cache.py # SQLite cache
│ ├── rate_limiter.py # Token bucket
│ ├── service.py # Orchestrator
│ ├── searcher.py # YouTube search
│ ├── search_cache.py # Search result cache
│ ├── search_service.py # Search orchestrator
│ ├── cuda_dll_manager.py # Auto-download CUDA libraries
│ └── exceptions.py # Custom exceptions
├── mcp_server/
│ ├── __init__.py
│ └── server.py # FastMCP server
├── cli.py # CLI entrypoint
├── main.py # Library entrypoint
├── config.py # Configuration
├── requirements.txt # Core dependencies
├── requirements-mcp.txt # MCP dependencies
├── README.md
└── QUICKSTART.md故障排除
"No module named 'rich'"
安装依赖项:
pip install -r requirements.txtWhisper 报错 "ffmpeg not found"
安装 ffmpeg (见上文安装部分)。
转录速度慢
使用较小的 Whisper 模型 (用
base代替large)通过在
whisper_runner.py中将device="cpu"改为device="cuda"来使用 GPU 加速启用缓存以避免重复转录
Innertube 速率限制
Innertube 回退方式受到 YouTube 的速率限制 (约 5 次请求/10 秒)。使用 Whisper 作为主要方式 (默认) 可避免此问题。缓存也能防止冗余请求。
缓存不工作
检查缓存统计信息:
python cli.py cache-stats清理过期条目:
python cli.py cache-stats --clean开发
运行测试
pytest格式化代码
black src/
ruff check src/许可证
MIT 许可证
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AndrewCTF/YTT'
If you have feedback or need assistance with the MCP directory API, please join our Discord server