Skip to content
SPECIFICTION
Get listed

spaCy

spacy.io

Free plan WindowsmacOSLinuxSelf-hosted
Visit spacy.io
Spec score 8.4 #2 of 28 in Natural Language Processing Software

What it is

spaCy is a free, open-source Python library for building natural language processing applications, with a focus on production use and large volumes of text. Its components handle named entity recognition, part-of-speech tagging, dependency parsing, sentence segmentation, text classification, lemmatization, morphology, and entity linking. The project lists support for 75+ languages and 84 trained pipelines for 25 languages, though trained pipelines are not available for every language. Developers can configure and train custom pipelines, describe training runs with configuration files, and package pipelines for installation as Python packages. spaCy can use pretrained transformers through spacy-transformers, and supports custom models in PyTorch, TensorFlow, and other frameworks. spaCy Projects supports workflows for downloads, commands, checksum verification, and caching, along with integrations for tracking, demos, model serving, distributed training, and Hugging Face Hub. Installation is available through pip, conda, or source on Linux, macOS, and Windows. The library can run on a user's servers without data leaving them. It is not a hosted software-as-a-service product or web application. The library is free under AGPL or a commercial license; transformer models require a GPU to run effectively.

Spec sheet

What it does
spaCy is a free, open-source Python library for advanced natural language processing, designed for production applications that process large volumes of text.Read 7 Oct 2026 · spacy.io
Purpose
spaCy is a Python library for advanced natural language processing, designed for production use and processing large volumes of text.Read 7 Oct 2026 · explosion.ai
Deployment
Trained pipelines can be installed as Python packages, and their data can be stored anywhere on the file system.Read 7 Oct 2026 · spacy.io
Integrations
The documentation describes integrations with transformer pipelines, CuPy for GPU support and an extension for Visual Studio Code configuration files.Read 7 Oct 2026 · spacy.io
Security
The official pages opened for this research did not state a security certification or compliance standard.Read 7 Oct 2026 · spacy.io
Support
The site links to GitHub Discussions, an issue tracker and Stack Overflow for community help.Read 7 Oct 2026 · spacy.io
Headquarters
Berlin, GermanyRead 28 Sep 2026 · spacy.io
Founded
2015Read 28 Sep 2026 · spacy.io
Maker
Explosion identifies itself as the maker of spaCy and describes itself as a software company specializing in developer tools and services for AI and natural language processing.Read 7 Oct 2026 · explosion.ai
Custom pipelines
Users can configure and train custom pipelines, package them as Python packages, and manage end-to-end workflows with spaCy Projects.Read 7 Oct 2026 · spacy.io
Data privacy
Explosion says spaCy can run without data leaving the user's servers.Read 7 Oct 2026 · explosion.ai
Framework integration
The homepage says spaCy supports custom models in PyTorch, TensorFlow and other frameworks.Read 7 Oct 2026 · spacy.io
Hardware limit
The documentation says transformer models require a GPU to run effectively, while word vectors are computationally efficient.Read 7 Oct 2026 · spacy.io
Installation
The documentation lists installation through pip, conda or source, with CPU and GPU options.Read 7 Oct 2026 · spacy.io
Language support
The maker’s homepage states that spaCy supports 75+ languages and offers 84 trained pipelines for 25 languages.Read 7 Oct 2026 · spacy.io
Languages
The site lists support for 75+ languages and 84 trained pipelines for 25 languages.Read 7 Oct 2026 · spacy.io
Model availability
The documentation notes that although spaCy supports tokenization for many languages, trained pipelines are not available for every language.Read 7 Oct 2026 · spacy.io
NLP features
Its components include named entity recognition, part-of-speech tagging, dependency parsing, sentence segmentation, text classification, lemmatization and morphological analysis.Read 7 Oct 2026 · spacy.io
NLP tasks
Its components cover named entity recognition, part-of-speech tagging, dependency parsing, sentence segmentation, text classification, lemmatization, morphology and entity linking.Read 7 Oct 2026 · spacy.io
Operating systems
The installation documentation says spaCy runs on Unix/Linux, macOS/OS X and Windows and is compatible with 64-bit CPython 3.7+.Read 7 Oct 2026 · spacy.io
Paid services
Explosion offers custom NLP consulting and implementation, with fees quoted up front; the page does not publish a price list.Read 7 Oct 2026 · explosion.ai
Product boundary
spaCy is a library for building NLP applications; it does not provide a software-as-a-service product or web application.Read 7 Oct 2026 · spacy.io
Project integrations
spaCy Projects describes integrations for data and experiment tracking, demos, model serving, distributed training and uploading pipelines to Hugging Face Hub.Read 7 Oct 2026 · spacy.io
Training
Its training system uses configuration files to describe training runs and make experiments reproducible.Read 7 Oct 2026 · spacy.io
Transformer integration
spaCy can load pretrained transformer models through spacy-transformers and supports sharing transformer embeddings across pipeline components.Read 7 Oct 2026 · spacy.io
Transformers
spaCy supports multi-task learning with pretrained transformers such as BERT and supports custom models in PyTorch, TensorFlow and other frameworks.Read 7 Oct 2026 · spacy.io
Workflow
The project system supports source asset downloads, command execution, checksum verification and caching with different backends and integrations.Read 7 Oct 2026 · spacy.io

Plans and prices

spaCy Free Free, open-source library; available under AGPL or a commercial license Read 7 Oct 2026 · explosion.ai

Every spaCy plan and price →

Strong points and limits

Strong points

  • Free, open-source library with AGPL or commercial licensing.
  • Supports 75+ languages and 84 trained pipelines for 25.
  • Custom pipelines can be packaged as Python packages.
  • Runs on Linux, macOS, and Windows.
  • Can run without data leaving the user's servers.

Limits

  • Trained pipelines are not available for every language.
  • Transformer models require a GPU to run effectively.
  • It is not a hosted SaaS product or web application.

Who it suits

spaCy suits developers building and deploying NLP applications, especially those processing large volumes of text. It is also relevant to teams that need configurable pipelines and control over where data is stored.

Verdict

spaCy offers a broad set of NLP components and tools for building custom production pipelines. Account for the difference between language tokenization support and trained pipeline availability, and check the licensing option that fits your use.

Where Specifiction places it

Alternatives to spaCyAll alternatives →