Live Captions API Is in Beta!
Published on June 1, 2023

The Vonage Live Captions API is in Beta and ready to be used in your application. Here are a few things to know.

Why Offer Live Captions?

Accessibility: It can not be assumed that everyone participating in a call can hear.

Noisy Environments: Even with the best noise-canceling headphones/earbuds, a loud area can be challenging.

Translation: It is just one more step to turn a caption into the language of the viewer.

Regain context: Missed what someone just said? You can most likely still see the caption in the feed.

Preference: According to a poll from YouGov, a sizeable amount of people prefer to have captions/subtitles on. I know I do.

YouGov poll asking When watching TV shows or movies in your native language, do you generally prefer to have the subtitles on or off? Overall 28% prefer subtitles on, 65% prefer subtitles off, 4% don't know, and 3% don't watch TV shows/movies YouGov poll asking When watching TV shows or movies in your native language, do you generally prefer to have the subtitles on or off? Overall 28% prefer subtitles on, 65% prefer subtitles off, 4% don't know, and 3% don't watch TV shows/movies

How the Live Captions API Works

The Live Captions API takes the audio streams (from both Video and SIP dial-in participants) that come through the Media Router and passes them to a transcription service.

Diagram showing how the Vonage Video Live Captions API works.Diagram showing how the Vonage Video Live Captions API works.

Advantages for developers

  • Live Captions are enabled by default for all projects.

  • Your application is already sending media streams to the Media Router.

  • No need to further strain your users' computers and/or mobile devices by sending another stream to be transcribed.

  • No third-party transcription library/service to learn and implement.

Enabling Live Captions in Your Application

A more detailed description can be found in the live captions documentation.

First, a POST request will need to be made to the Live Captions API endpoint with some credentials. Then you can use any of the many Client SDKs that we offer to interact with the API to start/stop sending and receiving captions.

Give It a Try

Instantly deploy a Basic Live Captions API demo to Stackblitz and point to a running server URL in config.js. The source code can be found in the GitHub repository.

Got Any Questions or Feedback?

We would love to hear from you. Please reach out to us on our Community Slack Channel. If you are on Twitter, follow the VonageDev account to receive the latest updates.

Dwane HemmingsJavaScript Developer Advocate

Ready to start building?

Experience seamless connectivity, real-time messaging, and crystal-clear voice and video calls-all at your fingertips.

Subscribe to Our Developer Newsletter

Subscribe to our monthly newsletter to receive our latest updates on tutorials, releases, and events. No spam.