[BUG] Reduced transcription fidelity in voice mode

Resolved 💬 2 comments Opened Mar 26, 2026 by brunoparga Closed Apr 25, 2026

Preflight Checklist

  • [x] I have searched existing issues and this hasn't been reported yet
  • [x] This is a single bug report (please file separate reports for different bugs)
  • [x] I am using the latest version of Claude Code

What's Wrong?

Voice mode sometimes just hallucinates words that were never said. For example, at one point it transcribed the word "voice" as "brain". These words are as dissimilar as "yanny" and "laurel".

What Should Happen?

Transcription is as faithful as it used to be.

Error Messages/Logs

Steps to Reproduce

Use voice mode, preferably by someone that's not a native speaker of the language being used. Random words will eventually appear.

Claude Model

Sonnet (default)

Is this a regression?

Yes, this worked in a previous version

Last Working Version

Possibly 2.1.83

Claude Code Version

2.1.84 (Claude Code)

Platform

Anthropic API

Operating System

Ubuntu/Debian Linux

Terminal/Shell

Other

Additional Information

Kitty terminal

View original on GitHub ↗

This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗