ML Kit brings Google’s machine learning expertise to mobile developers in a powerful and easy-to-use package. Make your iOS and Android apps more engaging, personalized, and helpful with solutions that are optimized to run on device.
ML Kit’s processing happens on-device. This makes it fast and unlocks real-time use cases like processing of camera input. It also works while offline and can be used for processing images and text that need to remain on the device.
Take advantage of the machine learning technologies that power Google's own experiences on mobile.
We combine best-in-class machine learning models with advanced processing pipelines and offer these through easy-to-use APIs to enable powerful use cases in your apps.

Vision APIs

Video and image analysis APIs to label images and detect barcodes, text, faces, and objects.
Scan and process barcodes. Supports most standard 1D and 2D formats.
Detect faces and facial landmarks.
Detect face mesh info on close-range images.
Recognize and extract text from images.
Identify objects, locations, activities, animal species, products, and more. Use a general-purpose base model or tailor to your use case with a custom TensorFlow Lite model.
Localize and track in real time one or more objects in the live camera feed.
Recognizes handwritten text and handdrawn shapes on a digital surface, such as a touch screen. Recognizes 300+ languages, emojis and basic shapes.
Detect the position of the human body in real time.
Separate the background from users within a scene and focus on what matters.
Separate subjects (people, pets, or objects) from the background in a picture.
Digitize physical documents from pictures.

Natural language APIs

Natural language processing APIs to identify and translate between 58 languages and provide reply suggestions.
Determine the language of a string of text with only a few words.
Translate text between 58 languages, entirely on device.
Generate reply suggestions in text conversations.
Detect and locate entities (such as addresses, date/time, phone numbers, and more) and take action based on those entities. Works in 15 languages.