Built-in AI APIs

Alexandra Klepper

Published: August 27, 2024, Last updated: October 18, 2024

The following built-in APIs are only available to early preview program participants, in Chrome.

API status

API	Explainer	Web	Extensions	Chrome Status	Intent
Prompt API	GitHub	In EPP	In EPP	Not applicable	Not applicable
Summarizer API	GitHub	In EPP	In EPP	View	Intent to Prototype
Language Detector API	GitHub	Origin trial	Known bug	View	Intent to Experiment
Translator API	GitHub	In EPP	In EPP	View	Intent to Prototype
Writer API	GitHub	In EPP	In EPP	View	Intent to Prototype
Rewriter API	GitHub	In EPP	In EPP	View	Intent to Prototype

Prompt API

With the Prompt API, early preview program participants can send natural language requests to Gemini Nano in Chrome.

The Prompt API is an exploratory API, which means it's primarily intended for prototyping. We're asking for feedback to confirm assumptions and determine what task APIs we build in the future. As such, exploratory APIs may never launch.

Key Term: An explainer is a document that describes a proposed web platform feature or collection of features. As work progresses, explainers facilitate discussion and, hopefully, consensus around the approach and feature design. Explainers are updated as design progresses.

In Chrome Extensions

With the Prompt API exposed to Chrome Extensions, you can experiment in a real environment. Based on your findings, we can refine the API to better address real-world use cases.

For the Prompt API specifically, we aim to use a smaller scope to test ideas, so we can build a higher quality API.

Summarizer API

The Summarizer API is now available for local experimentation to our early preview program participants. With this API, you use built-in Gemini Nano to condense long-form content. Shorter content can be more accessible and useful to users.

The Writing Assistance APIs explainer is available as a proposal for the future development. You can help this proposal move to the next stage by indicating your support with a thumbs-up reaction or by commenting with details about your use cases and context.

Use cases

There are a number of use cases for summarization:

• Overview of a meeting transcript for those joining the meeting late or those who missed the meeting entirely.
• Key points from support conversations for customer relationship management.
• Sentence or paragraph-sized summaries of multiple product reviews.
• Key points from long articles, to help readers determine if the article is relevant.
• Generating draft titles for an article.
• Summarizing questions in a forum to help experts find those which are most relevant to their field of expertise.

Do you have additional ideas for a summarization API? Share them with us on GitHub.

Language Detector API

The Language Detector API lets you detect the language of texts. It's part of the concepts introduced in the Translator API explainer.

This API is in a Chrome origin trial.

Note: The Language Detector API is not yet available for Chrome Extensions. A bug has been filed, and we'll update this documentation once resolved.

Use cases

Language detection has several use cases:

• Determining the unknown source language for a following translation to a known target language, so the user doesn't have to specify both.
• Labeling texts, for example, to improve screen reader pronunciation in online social networking sites.

Do you have additional ideas for this API? Share them with us on GitHub.

Translator API

The Translator API is now available for early preview program participants. Translate user-generated and dynamic content on request.

Use cases

• Users can enter a request in their first language, which you can identify with the Language Detector API. Then, use the Translator API to convert the request to your business operating language and send it to a support agent.
• In a social network application, users can request a translation on-demand when a post appears on their timeline in a language they don't speak.

Share your thoughts on the API on GitHub.

Writer and rewriter APIs

The Writer API empowers you to create new content that conforms to a specified writing task, while the Rewriter API provides tools for revising and restructuring text. Both are part of the family of APIs introduced in the writing assistance APIs explainer. Help this proposal move to the next stage by indicating your support with a thumbs-up reaction or by commenting with details about your use cases and context.

Use cases

There are a number of use cases for writing and rewriting:

• Write based on an initial idea and optional context. For example, a formal email to a bank asking to increase the credit limit based on the context that you're a long-term customer.
• Refine existing text by making it longer or shorter, or changing the tone. For example, you could rewrite a short email so that it sounds more polite and formal.

Do you have additional ideas for a writer / rewriter API? Share them with us on GitHub.

Participate in early testing

We use your feedback to shape the future of these APIs, to ensure they meet the needs of developers and users.

Join our early preview program to experiment with early-stage built-in AI APIs.

In the meantime, you can learn how to use Gemini Pro on Google's servers with your websites and web apps in our quickstart for the Google AI JavaScript SDK.