claude-code - 💡(How to fix) Fix VSCode extension voice input forces English transcription, ignoring pt-BR system locale

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

The voice input button (microphone icon) in the Claude Code VSCode extension transcribes Portuguese (pt-BR) speech as English, producing gibberish output. The extension provides no configuration option to change the speech-to-text language.

Root Cause

The voice input button (microphone icon) in the Claude Code VSCode extension transcribes Portuguese (pt-BR) speech as English, producing gibberish output. The extension provides no configuration option to change the speech-to-text language.

Fix Action

Fix / Workaround

Workaround currently in use

Code Example

claudeCode.environmentVariables
claudeCode.useTerminal
claudeCode.allowDangerouslySkipPermissions
claudeCode.claudeProcessWrapper
claudeCode.respectGitIgnore
claudeCode.initialPermissionMode
claudeCode.disableLoginPrompt
claudeCode.autosave
claudeCode.useCtrlEnterToSend
claudeCode.preferredLocation
claudeCode.enableNewConversationShortcut
claudeCode.enableReopenClosedSessionShortcut
claudeCode.hideOnboarding
claudeCode.usePythonEnvironment

---

"claudeCode.voiceInputLanguage": {
  "type": "string",
  "default": "auto",
  "enum": ["auto", "en-US", "pt-BR", "es-ES", "fr-FR", "de-DE", "it-IT", "ja-JP", "zh-CN", "ko-KR"],
  "description": "Language for voice input transcription. 'auto' attempts to detect from speech or fall back to system locale."
}
RAW_BUFFERClick to expand / collapse

Description

The voice input button (microphone icon) in the Claude Code VSCode extension transcribes Portuguese (pt-BR) speech as English, producing gibberish output. The extension provides no configuration option to change the speech-to-text language.

Steps to reproduce

  1. Install Claude Code extension v2.1.140 on Windows 11
  2. Confirm system locale is pt-BR (via Get-Culture in PowerShell — returns pt-BR)
  3. Click the microphone button in the Claude chat input
  4. Speak any sentence in Portuguese
  5. Observe: transcription comes back as broken English

Example of actual output when speaking Portuguese:

"Hey, is it you now in Tenderl? Brookie. Burkendo printchi coaching v a. alioclaudge coach"

(Portuguese phonemes are being force-mapped to English words.)

Expected behavior

Any of the following would solve this:

  • Auto-detect language from speech
  • Respect Windows system locale (pt-BR in this case)
  • Expose a claudeCode.voiceInputLanguage setting in the extension configuration

Actual behavior

Transcription is always forced to English. Non-English phonemes are mapped to English words, producing nonsensical output that's unusable.

Environment

  • OS: Windows 11 Pro
  • Claude Code VSCode extension: 2.1.140 (latest as of report)
  • Windows system language: pt-BR
  • Windows speech services: pt-BR installed and working

Settings reviewed

I checked all 13 settings exposed by the extension — none relate to voice, language, or locale:

claudeCode.environmentVariables
claudeCode.useTerminal
claudeCode.allowDangerouslySkipPermissions
claudeCode.claudeProcessWrapper
claudeCode.respectGitIgnore
claudeCode.initialPermissionMode
claudeCode.disableLoginPrompt
claudeCode.autosave
claudeCode.useCtrlEnterToSend
claudeCode.preferredLocation
claudeCode.enableNewConversationShortcut
claudeCode.enableReopenClosedSessionShortcut
claudeCode.hideOnboarding
claudeCode.usePythonEnvironment

Workaround currently in use

Using Win + H (Windows native dictation) which respects pt-BR locale correctly. Works fine, but defeats the convenience of the integrated extension mic button.

Impact

Non-English speakers cannot effectively use the voice input feature. This affects users speaking Portuguese, Spanish, French, German, Italian, Japanese, and any other non-English language — likely a large portion of the international user base.

Suggested fix

Add a configuration option:

"claudeCode.voiceInputLanguage": {
  "type": "string",
  "default": "auto",
  "enum": ["auto", "en-US", "pt-BR", "es-ES", "fr-FR", "de-DE", "it-IT", "ja-JP", "zh-CN", "ko-KR"],
  "description": "Language for voice input transcription. 'auto' attempts to detect from speech or fall back to system locale."
}

Either auto-detection or an explicit selector would solve the issue.


Happy to provide additional logs or test fixes. Thanks!

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

Any of the following would solve this:

  • Auto-detect language from speech
  • Respect Windows system locale (pt-BR in this case)
  • Expose a claudeCode.voiceInputLanguage setting in the extension configuration

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING