Speakable (BETA)

The speakable schema.org property identifies sections within an article or webpage that are best suited for audio playback using text-to-speech (TTS). Adding markup allows search engines and other applications to identify content to read aloud on Google Assistant-enabled devices using TTS. Web pages with speakable structured data can use the Google Assistant to distribute the content through new channels and reach a wider base of users.

The Google Assistant uses speakable structured data to answer topical news queries on smart speaker devices. When users ask for news about a specific topic, the Google Assistant returns up to three articles from around the web and supports audio playback using TTS for sections in the article with speakable structured data. When the Google Assistant reads aloud a speakable section, it attributes the source and sends the full article URL to the user's mobile device through the Google Assistant app.


The following is an example of speakable structured data using JSON-LD code and the xPath content-locator value:

    <title>Speakable markup example</title>
    <meta name="description" content="This page is all about the quick brown fox" />
    <script type="application/ld+json">
     "@context": "https://schema.org/",
     "@type": "WebPage",
     "name": "Quick Brown Fox",
      "@type": "SpeakableSpecification",
      "xPath": [
     "url": "http://www.quickbrownfox_example.com/quick-brown-fox"

Country and language availability

The speakable property works for users in the U.S. that have Google Home devices set to English, and publishers that publish content in English. We hope to launch in other countries and languages as soon as sufficient number of publishers have implemented speakable.

Getting started

For your news content to be eligible as answers to topical news queries, follow these steps:

  1. Make sure that you follow our guidelines.
  2. Add speakable structured data to your web page.
  3. Submit your content to begin the onboarding process. After you submit your content, the review can take up to five business days. Once complete, Google sends you a notification to let you know whether your content is eligible or not.


You must follow these guidelines for speakable content to be eligible to appear in news results.

Technical guidelines

Follow these guidelines when implementing speakable markup for Google Assistant.

  • Don't add speakable structured data to content that may sound confusing in voice-only and voice-forward situations, like datelines (location where the story was reported), photo captions, or source attributions.
  • Rather than highlighting an entire article with speakable structured data, focus on key points. This allows listeners to get an idea of the story and not have the TTS readout cut off important details.

Content guidelines

Follow these guidelines when writing content that you intend to mark up with speakable structured data.

  • Content indicated by speakable structured data must have concise headlines and/or summaries that provide users with comprehensible and useful information.
  • If you include the top of the story in speakable structured data, we suggest that you rewrite the top of the story to break up information into individual sentences so that it reads more clearly for TTS.
  • For optimal audio user experiences, we recommend around 20-30 seconds of content per section of speakable structured data, or roughly two to three sentences.

Structured data type definitions

Speakable is used by the Article or Webpage object. The full definition of speakable is available at schema.org/speakable. You must include the required properties for your content to be eligible for this feature.

The speakable property can be repeated an arbitrary number of times, with two kinds of possible content-locator values: CSS selectors and xPaths. Use one of the following properties:

Required properties


Addresses content in the annotated pages (such as class attribute). Use either cssSelector or xPath; don't use both. For example:

  "@type": "SpeakableSpecification",
  "cssSelector": [


Addresses content using xPaths (assuming an XML view of the content). Use either cssSelector or xPath; don't use both. For example:

  "@type": "SpeakableSpecification",
  "xPath": [


If you're having trouble implementing or debugging structured data, here are some resources that may help you.

Can't trigger content

Problem: You can't trigger your content through the Google Assistant using TTS audio.

Fix the issue

  1. Try the following voice commands:
    • "What's the latest news about $topic?"
    • "What's the latest on $topic?"
    • "Play news about $topic."
  2. If you're still having trouble, it may be because ranking is determined algorithmically. The Google Assistant provides up to three articles from different news publications through TTS audio playback. For more information about how Google ranks articles, see How Search works.

Other issues

Problem: You're experiencing other issues not covered by the documentation.

Fix the issue

  1. Visit the Google Search Central Help Community.
  2. Contact your Google representative or audio news support.

More audio solutions

In addition to speakable structured data, you can use other Google Assistant audio solutions for your news content, such as advanced integration of Google Assistant for your own custom applications. For example, allowing users to interact with the app through Google Assistant. For more information, see the Actions on Google developer guide.