ReadSpeaker speechCloud API (SCAPI) is a server-based web service that converts text sent to the ReadSpeaker server into speech/audio using text-to-speech technology (TTS), which is then sent back to the customer’s server.

ReadSpeaker has now added the possibility to request timing information to be included with the speech output. Access to timing information makes it possible to build a highlighting solution. Developers can now speech enable mobile apps and other applications and have the text highlighted simultaneously.

The timing information can be requested in two different ways:
1. In a separate call to the server. This will return a JSON object with timing information.
2. By requesting the audio format RSDS. This format contains both the audio and timing information. This means just one call to our server.

Use Cases
Highlighting is undoubtedly the most important use case for which this new feature is needed. But here are some other use cases which also need the timing information feature. Now that you can keep track of where a user is in a text, you can also add functionality for:

  1. Adding bookmarks. If there’s a long text and the user can’t listen to it all in one sitting, you could create a bookmark solution that holds the spot in the text where the user last listened to so that she or he can easily come back to it when ready.
  2. Multi-device listening. If the user begins listening to a text on a computer, and then wishes to continue listening on a smartphone on the way home from work or school, you can create a solution that allows switching from one device to another.
  3. Navigating in the audio. You can build a solution that allows the user to fast forward to a specific place in the text by clicking where they wish the reading to start.
  4. Reorganizing the audio. You can let the user select, copy/paste, and move around parts of the audio by working with specific areas of a text.
  5. Using avatars. If you use avatars, you can customize when they should speak within a text.
  6. Detailed statistics of listening patterns. You can track and see which parts of a text users tend to listen to more than others.

All of these use cases could be valuable for publishers, newspapers, teaching platforms, or any content owner who thinks highlighting or any other features based on timing information could be useful for their users.

For further information on ReadSpeaker speechCloud API, please visit the dedicated page: https://www.readspeaker.com/solutions/text-to-speech-online/readspeaker-speechcloud-api/

If you have any questions regarding the use of this new feature, please contact us.