twelvelabs
Decision gist · record as of 2026-08-14
Yes, if you are building on the TwelveLabs platform and want to avoid writing raw HTTP boilerplate. The SDK is actively maintained, has low install friction, and supports current Python versions. However, verify the license terms first—they are not declared in the package metadata. Also confirm that the free tier API key and rate limits suit your use case, as the SDK is a client library and all video processing happens on TwelveLabs' servers.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires a TwelveLabs API key and account (free tier available); Python 3.8 or newer.
- Low install friction with pure-Python wheels and a small dependency footprint (httpx, pydantic, and typing utilities).
- Active maintenance as of 22 days ago.
License · maintenance · safety
(unclear) — License treatment is unclear; no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before use in proprietary or copyleft-sensitive projects.
last release 2026-07-23 (22 days)
0 known vulnerabilities (OSV.dev, 2026-08-14) · 380,289 downloads/mo, #7,104 on PyPI
Alternatives
Verify before relying
pip install twelvelabs
from twelvelabs import TwelveLabs
client = TwelveLabs(api_key="<YOUR_API_KEY>")
index = client.indexes.create(
index_name="my_index",
models=[{"model_name": "marengo3.0", "model_options": ["visual", "audio"]}]
)
print(f"Created index: id={index.id}")- Whether the license is open-source, proprietary, or dual-licensed (metadata is unclear).
- Actual API rate limits and pricing tier constraints for the free account tier.
- Whether video files larger than 4 GB are supported despite the guide mentioning 4 GB as a limit for the guide only.
What it is and what it does
The TwelveLabs SDK is a Python client library that wraps the TwelveLabs video understanding platform's HTTP API, reducing boilerplate code for common workflows. It provides object-oriented interfaces for creating video indexes, uploading video assets (from URLs or local files), monitoring processing status, and querying videos using natural language text or image-based search across visual and audio modalities.
The SDK is built on httpx for HTTP communication and pydantic for data validation, supporting Python 3.8 through 3.12. Typical workflows involve creating an index configured with specific AI models (such as Marengo for search or Pegasus for text generation), uploading videos, waiting for indexing to complete asynchronously, and then performing downstream tasks like semantic video search or content analysis. The platform handles video understanding internally; the SDK's role is to orchestrate these operations and parse results.
Use it for
- Build a video search engine that finds clips matching natural language queries across a library of indexed videos.
- Automate video ingestion and indexing workflows by uploading files and monitoring processing status programmatically.
- Generate text summaries or descriptions of video content by indexing with the Pegasus model and calling analysis endpoints.
- Integrate video understanding into a larger application (e.g., a content management or discovery platform) without writing raw HTTP calls.
- Search video archives by visual content (objects, scenes) or audio (spoken words, sounds) using multimodal queries.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you are building on the TwelveLabs platform and want to avoid writing raw HTTP boilerplate.
The SDK is actively maintained, has low install friction, and supports current Python versions. However, verify the license terms first—they are not declared in the package metadata. Also confirm that the free tier API key and rate limits suit your use case, as the SDK is a client library and all video processing happens on TwelveLabs' servers.
Install
twelvelabs on PyPI
Before you install
Low install friction with pure-Python wheels and a small dependency footprint (httpx, pydantic, and typing utilities). Active maintenance as of 22 days ago.
Requires a TwelveLabs API key and account (free tier available); Python 3.8 or newer.
License in practice
License treatment is unclear; no SPDX identifier or raw license text is available in the package metadata. Verify the actual license terms before use in proprietary or copyleft-sensitive projects.
Quickstart
pip install twelvelabs
from twelvelabs import TwelveLabs
client = TwelveLabs(api_key="<YOUR_API_KEY>")
index = client.indexes.create(
index_name="my_index",
models=[{"model_name": "marengo3.0", "model_options": ["visual", "audio"]}]
)
print(f"Created index: id={index.id}")Verify before relying
- Whether the license is open-source, proprietary, or dual-licensed (metadata is unclear).
- Actual API rate limits and pricing tier constraints for the free account tier.
- Whether video files larger than 4 GB are supported despite the guide mentioning 4 GB as a limit for the guide only.
Package facts
| License | Not declared unclear |
| Python support | Supports the current Python release <4.0,>=3.8 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 5 packageshttpxhttpx-ssepydanticpydantic-coretyping_extensions |
| Maintenance | Actively maintained 22 days since the last release |
| First released | |
| Downloads | 380,289 / month, #7,104 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Intended Audience :: DevelopersOperating System :: MacOSOperating System :: Microsoft :: WindowsOperating System :: OS IndependentOperating System :: POSIXOperating System :: POSIX :: LinuxProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.8Programming Language :: Python :: 3.9Topic :: Software Development :: Libraries :: Python ModulesTyping :: Typed |
Evidence: twelvelabs-1.3.1-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “video search and indexing sdk”
- twelvelabsPython SDK for the TwelveLabs video understanding platform, providing…
- aurelio-sdkClient library for the Aurelio Platform that provides APIs for…
- glean-api-clientA Python SDK for accessing Glean's REST API, providing type-hinted…
Give your agent the search over MCP, or paste the wish link into any chat.
More Python Modules packages
Converts domain names between Unicode and ASCII-compatible encoding (Punycode) according to IDNA 2008 and Unicode Technical Standard 46, with security validation and broader script coverage than the standard library.
Install it if you work with internationalized domain names, need to validate domains, or use HTTP clients that depend on it transitively.
Setuptools is a Python build backend and package management tool that handles building, distributing, and installing Python packages, including support for C/C++ extension modules.
PyYAML parses and emits YAML 1.1 data format, enabling serialization and deserialization of configuration files and Python objects to and from human-readable YAML text.
Pydantic validates Python data structures against type hints, coercing and checking input at runtime to ensure it matches a declared schema.
Provides reusable metadata objects for use with PEP-593 `typing.Annotated` to express common constraints like bounds, collection sizes, and predicates on types.
Install it if you use or build libraries that need to express type constraints in a standardized, inspectable way—or if you want to annotate your own types with…
Provides runtime tools to inspect and introspect Python type annotations, enabling programmatic examination of type hints at execution time.
See also mux-python · youtube-search-python · pytube · metal-sdk · cloudinary · azure-search-documents · zai-sdk · firecrawl · google-cloud-videointelligence · contentful