getyoutubetranscript-haystack
A Haystack component that fetches YouTube video transcripts as Documents, powered by the GetYouTubeTranscript API. Use it in RAG pipelines, or wrap it as a tool for Haystack agents.
The API fetches transcripts on its own servers, so it works from cloud servers without proxies, and without RequestBlocked / IpBlocked errors.
Install
pip install getyoutubetranscript-haystack
Get an API key at getyoutubetranscript.com/dashboard (free tier included):
export GETYOUTUBETRANSCRIPT_API_KEY=sk_live_...
Usage
from haystack_integrations.components.fetchers.getyoutubetranscript import GetYouTubeTranscriptFetcher
fetcher = GetYouTubeTranscriptFetcher()
documents = fetcher.run(videos=["https://youtu.be/jNQXAC9IVRw", "5e37ZT3SQbk"])["documents"]
print(documents[0].meta)
# {'url': 'https://www.youtube.com/watch?v=jNQXAC9IVRw', 'video_id': 'jNQXAC9IVRw', 'title': 'Me at the zoo',
# 'author_name': 'jawed', 'language_code': 'en', 'word_count': 39}
One Document per video. Parameters:
| Parameter | Default | Description |
|---|---|---|
api_key |
Secret.from_env_var("GETYOUTUBETRANSCRIPT_API_KEY") |
API key |
language |
None |
Caption language code, e.g. "en" |
timestamps |
False |
content becomes [m:ss] lines, and meta["segments"] holds {start, duration, text} per caption line |
raise_on_failure |
True |
If False, videos that fail (no captions, invalid ID) are logged and skipped |
In a RAG pipeline
from haystack import Pipeline
from haystack.components.preprocessors import DocumentSplitter
from haystack.components.writers import DocumentWriter
from haystack.document_stores.in_memory import InMemoryDocumentStore
from haystack_integrations.components.fetchers.getyoutubetranscript import GetYouTubeTranscriptFetcher
store = InMemoryDocumentStore()
indexing = Pipeline()
indexing.add_component("fetcher", GetYouTubeTranscriptFetcher())
indexing.add_component("splitter", DocumentSplitter(split_by="word", split_length=200))
indexing.add_component("writer", DocumentWriter(document_store=store))
indexing.connect("fetcher.documents", "splitter.documents")
indexing.connect("splitter.documents", "writer.documents")
indexing.run({"fetcher": {"videos": ["https://youtu.be/5e37ZT3SQbk"]}})
As an agent tool
from haystack.tools import ComponentTool
from haystack_integrations.components.fetchers.getyoutubetranscript import GetYouTubeTranscriptFetcher
youtube_tool = ComponentTool(
component=GetYouTubeTranscriptFetcher(timestamps=True),
name="youtube_transcript",
description="Get the transcripts of YouTube videos from their URLs or IDs.",
)
The component serializes with to_dict() / from_dict(), keeping the key as an environment variable reference, so pipelines can be saved as YAML.
Pricing
Each transcript uses one credit from your GetYouTubeTranscript account. Failed requests are not charged.
Links
- GetYouTubeTranscript API docs
- Python SDK (this package is built on it)
- License: MIT
Metadata
Release files for getyoutubetranscript-haystack 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| getyoutubetranscript_haystack-0.1.0.tar.gz | 5.4 kB | Without provenance | Details for getyoutubetranscript_haystack-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| getyoutubetranscript_haystack-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for getyoutubetranscript_haystack-0.1.0-py3-none-any.whl |
Total release size: 11.2 kB
Release files / getyoutubetranscript_haystack-0.1.0.tar.gz
| Download URL | getyoutubetranscript_haystack-0.1.0.tar.gz |
|---|---|
| Size | 5.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f308827deaeabd30a0a3788d2f4751e52d397c1b8dadece7793a0445013bd665
|
|
BLAKE2b-256 checksum How to use checksums |
80d9f04c42290c17b6e214bd9c98b626195596c9b92768c94d8bda6136a4cb8a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.0
|
Release files / getyoutubetranscript_haystack-0.1.0-py3-none-any.whl
| Download URL | getyoutubetranscript_haystack-0.1.0-py3-none-any.whl |
|---|---|
| Size | 5.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e1398e8c59dde6cd7481c3d38848741529d325c67681490d8e1ca0d8af46d474
|
|
BLAKE2b-256 checksum How to use checksums |
f28ca82a41edfc117b366a33e7043bd66da8c147dc28d70929cdc785abde5603
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.11.0
|
Security for getyoutubetranscript-haystack 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.