AI UX PlaygroundNewsletterJoin 2K+ AI designers and PMs on Substack. New teardowns, patterns, and prompts as they drop.

Inputs

Input Mode Toggle

Switch between text, voice, dictation, or other composer modes without losing draft context. Put the control near the input so changing modality is intentional.

Interactive demo

How can I help?

Overview

How might we design input mode toggle so people can trust and act on AI output?

When to use

  • Essential for AI assistants, mobile applications, and accessibility-focused tools where supporting multiple input modes improves user experience and accessibility.

When to skip

  • Text-only products with no alternate modality.
  • Voice-only devices where a toggle would be meaningless.
  • Modes that wipe the draft on switch without warning.

Rules

  • Hidden mode switches buried in settings.

  • Switching modes that discard the in-progress draft.

  • Ambiguous icons with no label for voice vs dictation vs call.

  • Forcing a mode based on device without an override.

Evidence

ProductImplementation
ChatGPTComposer controls to enter voice mode from text chat.
Google GeminiMic and text entry toggles on the home composer.
ClaudeVoice and text input options on the chat surface.
PerplexityVoice and text modes for search-style queries.

Real-world examples

See all

FAQ

What is an input mode toggle?

It is a control that switches how users enter prompts (text, voice, dictation) while keeping them in the same composer context.

Should the draft survive a mode switch?

Yes whenever possible. Converting voice partials into editable text before leaving voice mode is a common pattern.

How does this differ from multimodal input?

Multimodal input attaches images or files alongside text. Mode toggle changes the primary entry modality itself.

Where should the toggle live?

Adjacent to the composer send controls. Settings-only mode switches are too slow for moment-to-moment use.