Choosing an Input Mode

Bourne AI supports three input modes: voice, text, and camera. You can use one mode throughout a session or combine modes depending on the job. Mode selection is made when you start a session, and within a session you can draw on each mode as the work requires.

Voice Mode

Voice mode lets workers talk to the system — advancing steps, asking questions, and confirming completions by speaking. The AI listens and responds in kind.

Best for: hands-free environments where gloves, machinery, or outdoor conditions make tapping a phone impractical.

Requirements: microphone permission must be granted in the browser. The browser will prompt for this on first use. On most devices you can review this permission under the site settings in your browser.

Text Mode

Text mode lets workers type responses into the interface. The AI reads each entry and responds as it would in any other mode.

Best for: noisy environments where voice recognition is unreliable, or quiet areas such as office spaces, clean rooms, or occupied customer sites where speaking aloud is disruptive.

Requirements: any device with a keyboard or on-screen keyboard. No additional permissions are needed.

Camera Mode

Camera mode lets workers point their phone at the work. Bourne AI processes the camera frame and can confirm a step, identify a part or label, or surface relevant knowledge based on what it sees.

Best for: visual inspection, part identification, condition assessment, and any step where what the worker is looking at needs to carry into the guidance.

Requirements: camera permission must be granted in the browser. A rear-facing camera is required for most field use cases.

See Camera Input & Identification for the full capability, including how the system matches what the camera sees against your uploaded image library.

Combining Modes

A single session can use all three modes. A common pattern is voice for step navigation — keeping hands free — combined with camera at specific steps that require a visual check. Text can be used at any point for follow-up questions or when voice is not practical.

The system handles the transition between modes without interrupting the session. Workers can move between modes as conditions change.

Device Requirements

  • All modes: any modern smartphone running a current browser (Chrome, Safari, or equivalent)
  • Voice mode: microphone access; works on both iOS and Android
  • Text mode: on-screen or physical keyboard; no additional hardware required
  • Camera mode: rear-facing camera; camera permission granted in the browser

How to Switch Modes

Mode is configured when you start a session. Within a session you can engage any available mode at any step — tap the camera icon to switch to camera input, or speak to use voice when microphone access is active. You are not locked into a single mode for the duration of a session.