Skip to main content

Real-time voice

Real-time voice lets you have natural, hands-free voice conversations with Glean. Instead of typing, you speak and hear Glean respond out loud, with interruptible back-and-forth dialogue. Conversations are transcribed into a standard chat so you can scroll, copy, or continue by text later.

Real-time voice is different from dictation or text-to-speech. It enables low-latency, interactive dialogue where you can interrupt, ask follow-up questions, and receive spoken answers grounded in your organization's knowledge.

note

Real-time voice is available for Glean Universal Model Key customers only. The feature is on by default, but your admin can disable it. If you don't see the voice button, contact your Glean admin. For admin configuration details, see Real-time voice setup.

Where to access

Real-time voice is available on web, desktop, and mobile. Look for the voice button (waveform icon) in the composer.

Get started

  1. Open Glean.
  2. Tap or click the voice button (waveform icon) in the composer.
  3. Grant microphone access if prompted. You only need to do this the first time.
  4. Start talking. Glean listens and responds out loud. You can interrupt at any time.
  5. When you're done, end the voice session. You can also read the conversation on screen by switching to Chat in the ribbon. Your conversation is saved as a standard chat transcript that you can review, copy, or continue by text.

Create documents by voice

You can create document artifacts directly from a voice conversation. Instead of receiving a transient chat response, Glean generates a persistent document that appears in the Canvas and is saved to your Library.

This is useful when a spoken conversation produces something you want to keep, such as a project brief drafted during a brainstorming session, a follow-up email captured as a doc, or a working document from a planning discussion.

How it works

  1. During a voice session, ask Glean to create a document. For example, "Draft a one-page project brief on Q3 priorities as a document."
  2. The document artifact appears and updates live in the Canvas while you continue the conversation.
  3. When the session ends, the document is saved to your Library as a reusable artifact you can revisit, edit, and share.
note

Only document artifacts are supported from voice at this time. Slides, HTML, and other visual artifact types must be created from text chat.

Use cases

Real-time voice works well for situations where typing isn't practical or when a spoken conversation feels more natural:

  • Brainstorm and capture as a document: Talk through ideas and have Glean create a project brief or working doc from the conversation, saved to your Library for later editing.
  • Prepare for the day: Ask about your upcoming meetings, open action items, or key updates while getting ready.
  • Hands-free document and knowledge Q&A: Query internal documents, policies, or project details without switching windows.
  • Triage email and messages: Catch up on your inbox while commuting. Have Glean summarize new messages and flag what needs attention.
  • Rehearse difficult conversations: Practice a challenging discussion with Glean playing the other side.
  • Untangle messy projects: Talk through a complex project and let Glean help you organize your thoughts and surface relevant information.
  • Reflect on your week: Review what you accomplished and plan ahead using voice while wrapping up for the week.

Privacy and data handling

  • No raw audio is stored. Audio streams are routed from your browser through Glean servers to OpenAI and back. No audio recordings are retained.
  • Transcriptions are stored like text chats. Voice transcriptions follow the same storage and retention policies as standard chat messages.
  • Permissions are enforced. Glean's existing security model and document-level permissions apply to all voice interactions, the same as text-based chats.

Limitations

  • Real-time voice is available for Glean Universal Model Key customers only. Customer Key support is not yet available.
  • Only document artifacts can be created from voice at this time. Slides, HTML, and other visual artifact types must be created from text chat.
  • Real-time voice usage may be subject to usage-based pricing.

Frequently asked questions