[DOCS] Voice mode and `voiceEnabled` settings are undocumented in Claude Code docs
Documentation Type
Missing documentation (feature not documented)
Documentation Location
https://code.claude.com/docs/en/settings
Section/Topic
Voice mode setup, push-to-talk behavior, and voiceEnabled settings reference.
Current Documentation
No documentation currently exists for voice mode setup, push-to-talk behavior, or the voiceEnabled setting in the settings reference.
The interactive command table currently documents many slash commands (for example /mcp, /plugin, /rename, /usage, /vim) but does not document a voice command workflow.
What's Wrong or Missing?
v2.1.70 release notes include multiple voice-related user-facing behaviors:
- Voice mode runtime behavior on Windows
- Push-to-talk activation when
voiceEnabled: trueis set in settings - Microphone silence error messaging
These entries imply voice functionality and settings are available to users, but the primary docs do not describe how to enable, configure, or operate voice mode.
Suggested Improvement
Add voice documentation that covers:
- How to enable/disable voice mode (
voiceEnabled) and where it is configured. - Push-to-talk behavior and session-start expectations.
- Platform caveats (for example Windows/WSL notes) and troubleshooting for silence/no-speech capture.
- Command/UI entry points for voice mode in CLI and IDE surfaces.
Impact
Medium - Makes feature difficult to understand
Additional Context
Affected Pages:
| Page | Line(s) | Context |
|------|---------|---------|
| https://code.claude.com/docs/en/settings | 167-203 | Settings key tables have no voice/voiceEnabled coverage |
| https://code.claude.com/docs/en/interactive-mode | 116-157 | Slash command table has no documented voice-mode command entry |
Total scope: 2 pages affected
Source: Release v2.1.70
- Fixed voice mode failing on Windows native binary with "native audio module could not be loaded"
- Fixed push-to-talk not activating on session start when
voiceEnabled: truewas set in settings - Improved error message when microphone captures silence to distinguish from "no speech detected"
This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗