Perfect Diarization

📘

Supported Platforms

Perfect diarization is currently supported for Zoom Native and Teams Web bots.

Perfect diarization is a feature designed to address the problem of inaccurate speaker attribution in meeting transcripts. Meeting platforms can sometimes attribute words to the wrong speaker, especially when multiple people are talking at once. This feature ensures that each speaker's words are accurately identified, even when participants are talking over each other.

How It Works

Perfect diarization transcribes separate audio streams for each participant instead of using the combined audio stream for the entire meeting, significantly improving the accuracy of speaker attribution. This feature is compatible with all AI transcription providers supported by Recall.ai and can be used for real-time transcription.

Requesting Access

Perfect diarization is currently feature flagged and needs to be enabled for your workspace by the Recall.ai team. Reach out via Slack or email to set this up.

Usage

To enable perfect diarization, add the use_separate_streams_when_available parameter to transcription_options when calling Create Bot:

{
  ...,
  "transcription_options": {
    "provider": "Your AI Transcription Provider",
    "use_separate_streams_when_available": true
  }
}

If you're sending the bot to a Teams call, no further configuration is needed on your end! If you're sending the bot to a Zoom call, you'll need to use a Zoom Native bot. You can specify this by adding the following parameter to the Create Bot request:

  "variant": {
    "zoom": "native",
  }

Important Considerations

Increased Transcription Usage: Transcribing multiple streams may result in higher costs from your transcription provider. On average, usage is ~1.8x higher than single-stream transcription.