Python reader

YouTube transcripts in LlamaIndex

GetYouTubeTranscriptReader has the same load_data(ytlinks=[...]) call as LlamaIndex's YoutubeTranscriptReader, but the transcripts are fetched by the GetYouTubeTranscript API. It keeps working on cloud servers where YouTube blocks direct requests.

Get your free credits Setup steps

Set it up

1
Install the reader
Into the same environment as llama-index:
```
pip install llama-index-readers-getyoutubetranscript
```
2
Get an API key
Sign in at getyoutubetranscript.com and create a key on the developers page (100 free credits, no card). Keys start with sk_live_. Set it as an environment variable:
```
export GETYOUTUBETRANSCRIPT_API_KEY=sk_live_...
```
3
Swap the import
If you used YoutubeTranscriptReader, change the import and class name; load_data(ytlinks=...) stays the same.

Build an index from a video

from llama_index.core import VectorStoreIndex
from llama_index.readers.getyoutubetranscript import GetYouTubeTranscriptReader

documents = GetYouTubeTranscriptReader().load_data(ytlinks=["https://youtu.be/5e37ZT3SQbk"])
index = VectorStoreIndex.from_documents(documents)
print(index.as_query_engine().query("What does the speaker say about education?"))

What you can build

A query engine over a course playlist or a creator's back catalog.
Timestamped retrieval: timestamps=True keeps {start, duration, text} segments in metadata, hidden from embeddings.
Multilingual indexes: pass language="es" (or any caption language) per call.

Questions about LlamaIndex

Which links does it accept?

Any YouTube URL (watch, youtu.be, Shorts, live) or an 11-character video ID.

Is the API key stored in serialized readers?

No. The key is read from the api_key argument or the environment and is never serialized.

What does it cost?

Each transcript, search or channel page uses one credit from your account, and failed requests are not charged. New accounts get 100 free credits, no card, and paid plans add more credits each month.