Voicemail to Text API Blog image2

Announcing the latest addition to the RingCentral for Developers growing library of APIs — the Voicemail Preview API uses a voicemail transcription service that produces a text-based preview of the audio voice message. This capability automatically transcribes the voicemail and makes the text available directly in the message object, enabling developers to add transcriptions easily to their mobile, web, or email applications.

The Voicemail Preview API is included with RingCentral Office Enterprise edition.

The Voicemail Preview API is offered as part of the Voicemail Preview feature in RingCentral Office Enterprise edition, providing text transcription across email, RingCentral for mobile and desktop, as well as for developers using the RingCentral Connect Platform.

The Voicemail Preview API imparts an enhanced customer experience when used with other cloud communications capabilities such as visual voicemail, call logs, screen pops, and integrations.

How are developers using the Voicemail Preview API?

Here are a few examples of how you can use this API:

  • Enhance visual voicemail: Enable visual voicemail management systems to display voicemail text in addition to metadata and audio playback.
  • Enhance call log search: Enable call logs already integrated with CRM and helpdesk solutions to log and search on voicemail messages.
  • Enhance screen pop effectiveness: Enable incoming calls to display voicemail text alongside caller information.

How does it work?

When a voicemail is received, RingCentral will transcribe the first minute of the email to text and make that available via the API. The Message Info object contains a new property, vmTranscriptionStatus, that indicates the transcription state. When the state is set to “Completed”, the transcription can be retrieved in the Message Info object using the “Get Single Message” and “Get Message List” messaging APIs as normal. Within the Message Info object, locate the “AudioRecording” attachment and retrieve the text file at the content endpoint. Voicemails will have two attachments, one in audio (MPEG) format and another in plain text format, the latter being the transcription.

API characteristics include:

  • Supported languages: English (US, GB) (en-US, en-GB)
  • Encoding: UTF-8
  • Content-Type: text/plain
  • Transcription latency: within minutes

An example message object response is shown below:

API Response Example
 “records” : [ {“uri” : “https://api.ringcentral.com/restapi/v1.0/account/1234567890/extension/1234567890/message-store/00000000001”,

“id” : 111111111111,

“to” : [ {

“name” : “(650) 555-1212 (John Wang)”

} ],

“from” : {

“phoneNumber” : “+14155551212”,

“name” : “WANG JOHN”,

“location” : “”


“type” : “VoiceMail”,

“creationTime” : “2015-04-01T00:00:14.000Z”,

“readStatus” : “Read”,

“priority” : “Normal”,

“attachments” : [ {

“id” : 10000000001,

“uri” : “https://api.ringcentral.com/restapi/v1.0/account/1234567890/extension/1234567890/message-store/00000000001/content/10000000001”,

“type” : “AudioRecording”,

“contentType” : “audio/mpeg”,

“vmDuration” : 27

}, {

“id” : 10000000002,

“uri” : “https://api.ringcentral.com/restapi/v1.0/account/1234567890/extension/1234567890/message-store/00000000001/content/10000000002”,

“type” : “AudioTranscription”,

“contentType” : “text/plain”

} ],

“direction” : “Inbound”,

“availability” : “Alive”,

“messageStatus” : “Received”,

“lastModifiedTime” : “2015-04-01T00:01:35.966Z”,

“vmTranscriptionStatus” : “Completed”

} ]


How can I get the API?

The Voicemail to Text feature is included for customers in the US and Canada using RingCentral Office Enterprise edition and it’s available for mobile and desktop applications, and email notifications. Customers interested in this feature are invited to upgrade to RingCentral Office Enterprise edition so they can explore the potential of this capability.