Skip to content

Speech-to-Text Integration Overview

Cloud Voice can connect to the Google Cloud Speech-to-Text API (Application Programming Interface, the service Google exposes for other systems to use) to convert incoming voicemail audio into readable text, so users can scan their messages instead of listening to each recording. This is often shortened to STT (Speech-to-Text), which you will see on the related disconnect page.

Keep the following limits in mind before you set up the integration:

  • The integration only works on a Cloud Voice system that can reach Google’s services. Systems without that connectivity are not supported.

Voicemail transcription in Cloud Voice is handled through a third-party transcription provider.

Once the integration is in place and Voicemail Transcription is turned on, users receive the transcribed text through these channels:

  • Cloud Voice App: the text for each voicemail is available in the Web, Desktop, and Mobile versions of the app.
  • Email: when Voicemail to Email is enabled, the transcription is included in the body of the voicemail notification email.