Use on-device machine learning in your apps to easily solve real-world problems.

![](https://developers.google.com/static/ml-kit/images/homepage/hero.png)

ML Kit is a mobile SDK that brings Google's on-device machine learning
expertise to Android and iOS apps. Use our powerful yet easy to use GenAI,
Vision and Natural Language APIs to solve common challenges in your apps or
create brand-new user experiences. All are powered by Google's best-in-class ML
models and offered to you at no cost.

ML Kit's APIs all run on-device, allowing for real-time use cases where you want
to process a live camera stream for example. This also means that the
functionality is available offline.

> [!NOTE]
> All ML Kit APIs require Android API level 23 or higher.

## What's new

[Video](https://www.youtube.com/watch?v=PoqJh_60Wrw)

- We launched the alpha version of [Prompt API](https://developers.google.com/ml-kit/genai/prompt/android.md.txt), which generates text content based on a custom text-only or multimodal prompt.
- We launched the beta version of the [GenAI APIs](https://developers.google.com/ml-kit/genai.md.txt), offering out-of-the-box quality for common use cases through a high-level interface. Initial launch includes [Image Description](https://developers.google.com/ml-kit/genai/image-description/android.md.txt), [Proofreading](https://developers.google.com/ml-kit/genai/proofreading/android.md.txt), [Rewriting](https://developers.google.com/ml-kit/genai/rewriting/android.md.txt) and [Summarization](https://developers.google.com/ml-kit/genai/summarization/android.md.txt).

## Learn more

- [Prompt API](https://developers.google.com/ml-kit/genai/prompt/android.md.txt) lets you send natural language requests on-device to Gemini Nano.
- [GenAI APIs](https://developers.google.com/ml-kit/genai.md.txt) harness the power of Gemini Nano to help your app perform tasks. These APIs provide out-of-the-box quality for popular use cases such as: [Image Description](https://developers.google.com/ml-kit/genai/image-description/android.md.txt), [Proofreading](https://developers.google.com/ml-kit/genai/proofreading/android.md.txt), [Rewriting](https://developers.google.com/ml-kit/genai/rewriting/android.md.txt) and [Summarization](https://developers.google.com/ml-kit/genai/summarization/android.md.txt).
- ML Kit also offers ready-to-use APIs powered by Google's ML models: [text recognition](https://developers.google.com/ml-kit/vision/text-recognition), [face detection](https://developers.google.com/ml-kit/vision/face-detection.md.txt), [barcode scanning](https://developers.google.com/ml-kit/vision/barcode-scanning.md.txt), [image labeling](https://developers.google.com/ml-kit/vision/image-labeling.md.txt), [object detection and tracking](https://developers.google.com/ml-kit/vision/object-detection.md.txt), [pose detection](https://developers.google.com/ml-kit/vision/pose-detection.md.txt), [selfie segmentation](https://developers.google.com/ml-kit/vision/selfie-segmentation.md.txt), [smart reply](https://developers.google.com/ml-kit/language/smart-reply.md.txt), [text translation](https://developers.google.com/ml-kit/language/translation.md.txt), and [language identification](https://developers.google.com/ml-kit/language/identification.md.txt).
- Learn how to use custom TensorFlow Lite image labeling models in your apps. Read [Custom models with ML Kit](https://developers.google.com/ml-kit/custom-models.md.txt).
- Take a look at our [sample apps and codelabs](https://developers.google.com/ml-kit/samples). They help you get started with all of the APIs.

## Other resources

If ML Kit's turn-key APIs don't meet your needs and you require a more custom
solution, visit the
[On-device Machine Learning page](https://developers.google.com/learn/topics/on-device-ml) for guidance on
all of Google's solutions and tools for on-device machine learning.