[FEATURE] Auto-format spoken file references in voice dictation

Resolved 💬 3 comments Opened May 13, 2026 by peytontucker Closed Jun 11, 2026

Preflight Checklist

  • [x] I have searched existing requests and this feature hasn't been requested yet
  • [x] This is a single feature request (not multiple features)

Problem Statement

When using /voice in Claude Code, spoken file references don't get normalized into usable format. For example, saying "orders controller dot R B" transcribes literally as "orders controller dot R B" rather than @orders_controller.rb.

Proposed Solution

Automatically recognize spoken file name patterns and convert them to properly formatted @file references to reduce time spent manually correcting/formatting transcriptions.

Alternative Solutions

Current workaround is manual replacement of erroneously-transcribed file references.

Priority

Medium - Would be very helpful

Feature Category

Interactive mode (TUI)

Use Case Example

  1. I'm using Claude Code voice transcription to draft a plan for a new feature
  2. I verbally reference relevant files while speaking
  3. The files are transcribed not as they are literally spoken, and but in a way that creates actual references to the files that provide the correct context to Claude Code

Additional Context

_No response_

View original on GitHub ↗

This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗