v1

latestOpenAPI 3.0.3RingCentral API License Agreement2026-08-064871,2921.5 MB
Insights

Interaction Analytics

Returns multiple insights including summaries, emotion, key phrases, questions asked, and more in a single API call.

post/ai/insights/v1/async/analyze-interaction

Query parameters

webhookstring uri required

The webhook URI to which the job response will be returned

Request body

contentUristring uri

Publicly facing uri

encoding'Mpeg' | 'Mp4' | 'Wav' | 'Webm' | 'Webp' | 'Aac' | 'Avi' | 'Ogg' required

The encoding of the original audio

languageCodestring required

Language spoken in the audio file.

sourcestring

Source of the audio file eg: Phone, RingCentral, GoogleMeet, Zoom etc

audioType'CallCenter' | 'Meeting' | 'EarningsCalls' | 'Interview' | 'PressConference' | 'Voicemail'

Type of the audio

separateSpeakerPerChannelboolean

Set to True if the input audio is multi-channel and each channel has a separate speaker.

speakerCountinteger

Number of speakers in the file, omit parameter if unknown

speakerIdsstring[]

Optional set of speakers to be identified from the call.

enableVoiceActivityDetectionboolean

Apply voice activity detection.

insightsInsightsEnum[]

Example request

{
  "encoding": "Wav",
  "languageCode": "en-US",
  "source": "RingCentral",
  "audioType": "CallCenter",
  "speakerCount": 2,
  "speakerIds": [
    "speakerId1",
    "speakerId2"
  ],
  "speechContexts": [
    {
      "phrases": [
        "Mohit",
        "Sushant",
        "RingCentral"
      ]
    }
  ]
}

Response

Task accepted for processing.

jobIdstring