How to beginner · 3 min read

How to load YouTube transcript with LangChain

Q: How to load YouTube transcript with LangChain

Use LangChain's YouTubeLoader class to load transcripts from YouTube videos by providing the video URL. This loader fetches the transcript automatically and returns it as documents ready for processing with LangChain.

Quick answer

Use LangChain's YouTubeLoader class to load transcripts from YouTube videos by providing the video URL. This loader fetches the transcript automatically and returns it as documents ready for processing with LangChain.

PREREQUISITES

Python 3.8+
pip install langchain>=0.2.0
pip install youtube-transcript-api
pip install requests
OpenAI API key (for downstream usage)

Setup

Install the required packages including langchain and youtube-transcript-api which LangChain uses internally to fetch YouTube transcripts.

bash

pip install langchain youtube-transcript-api requests

Step by step

Use LangChain's YouTubeLoader to load the transcript from a YouTube video URL. The loader returns a list of Document objects containing the transcript text.

python

from langchain_community.document_loaders import YouTubeLoader

# Replace with your YouTube video URL
video_url = "https://www.youtube.com/watch?v=dQw4w9WgXcQ"

loader = YouTubeLoader(video_url)
docs = loader.load()

for doc in docs:
    print(doc.page_content[:500])  # print first 500 chars of transcript

output

We're no strangers to love
You know the rules and so do I
A full commitment's what I'm thinking of
You wouldn't get this from any other guy
...

Common variations

Use YouTubeLoader with language parameter to specify transcript language if available.
Combine with LangChain text splitting or embeddings for downstream NLP tasks.
Use async loading by running loader.aload() in an async context.

python

import asyncio
from langchain_community.document_loaders import YouTubeLoader

async def load_async():
    loader = YouTubeLoader("https://www.youtube.com/watch?v=dQw4w9WgXcQ")
    docs = await loader.aload()
    for doc in docs:
        print(doc.page_content[:300])

asyncio.run(load_async())

output

We're no strangers to love
You know the rules and so do I
A full commitment's what I'm thinking of
You wouldn't get this from any other guy
...

Troubleshooting

If you get TranscriptDisabled error, the video has no transcript available or it is disabled.
Ensure the video URL is correct and publicly accessible.
Install youtube-transcript-api separately if LangChain loader fails to import it.

✅

Key Takeaways

Use LangChain's YouTubeLoader to fetch YouTube transcripts easily by URL.
Install youtube-transcript-api as it is required for transcript fetching.
You can load transcripts synchronously or asynchronously with LangChain.
Handle errors like missing transcripts by checking video availability and permissions.

Verified 2026-04

Verify ↗