Generate audio summaries and query documents using voice

  • Release version: Australia
  • Updated March 12, 2026
  • 1 minute to read
  • Generate audio summaries and interact using voice-based questions to understand and extract key information from documents.

    Before you begin

    Configure the Voice Assist for docs skill. For more information, see Configure Voice Assist for Docs skill.

    Warning:
    Voice Q&A uses Google's Gemini API. Your use of this feature is subject to the Google Gemini API Terms of Service or other applicable agreement you may have with Google governing your use of this API. You must grant microphone access to use voice Q&A.

    Role required: sn_voice_doc.user and admin defined roles

    Procedure

    1. Navigate to your workspace.
    2. Select a record from a list that has the Voice Assist for docs skill activated.
      For example, select an incident record.
    3. Open an attached document to view it in the document viewer.
      Note:
      • Maximum document size: 10 MB
      • Maximum pages: 30
      • Supported file types: pdf, docx, pptx, xlsx, doc, ppt, xls, jpeg, png
    4. Select the Ask Otto drop-down button Ask otto dropdown button icon
    5. Select Show Voice-Assist.
    6. For Audio Summary feature:
      1. Select Generate audio summary
      2. Select play button icon to generate an audio summary of the document.
      3. Select toggle button icon to view auto-generated transcript of the audio summary.
    7. For Voice Q&A feature:
      1. Select Start Voice Q&A to ask questions regarding the documents by using your voice.
      2. Select the check box in Voice Q&A-User Consent section.
      3. Select Grant access.
      4. Ask questions related to your document.
      5. To mute the microphone, select microphone icon
      6. To unmute the microphone, select unmute icon
      7. To generate live captions, select live caption icon
    8. When you finish, select End, to end the voice conversation.