[FEATURE] Voice input support for hands-free prompting in Claude Code CLI
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 working on long coding sessions, switching between typing code and typing prompts to Claude Code breaks flow. Voice input would allow users to describe what they want — explain a bug, request a refactor, ask a question — without lifting their hands from the keyboard or interrupting their train of thought.
This is especially valuable when thinking through architecture or debugging, where the cognitive load is high and typing a precise prompt adds friction. Currently there is no way to interact with Claude Code without text input, which limits its usefulness during active coding where hands and eyes are already occupied.
Proposed Solution
A push-to-talk hotkey (e.g. Cmd+Shift+Space) activates voice input in the CLI. A subtle indicator shows it's listening. When released, the audio is transcribed and dropped into the prompt field exactly as if it had been typed — the user can review and edit before hitting Enter, or configure it to auto-submit for trusted commands.
In the desktop app and IDE extensions, a microphone icon in the input bar serves the same purpose. No new UI, no separate mode — voice is just another way to fill the prompt.
Optionally, a "always listening" mode with a wake word (e.g. "Hey Claude") for fully hands-free operation during long sessions.
Transcription should happen locally where possible (Whisper) to avoid sending audio to a third-party service — keeping it consistent with Claude Code's existing privacy model.
Alternative Solutions
_No response_
Priority
High - Significant impact on productivity
Feature Category
Interactive mode (TUI)
Use Case Example
- I'm deep in a debugging session, eyes on the code, hands on the keyboard
- I spot a pattern I want Claude Code to refactor across multiple files
- Instead of stopping to type a prompt, I press a hotkey to activate voice input
- I say: "Refactor all the fetch functions in the services folder to use async/await instead of promise chains"
- Claude Code transcribes, confirms what it heard, and executes
- I stay in flow — no context switch, no typing, no interruption
Additional Context
_No response_
Showing cached comments. Read the full discussion on GitHub ↗
4 Comments
yes
Just use VoiceMode with Claude Code- It offers conversation, not just dictation.
https://voicemode.dev
I've had Airpods in ears, laptop in backpack and eyes on the scenery for a year now.
This matches a real workflow I see a lot in voice typing for AI coding. I maintain a small local-first macOS voice typing app for Chinese / Chinese-English input: https://github.com/botaruibo/MyVoiceTyping
The most common use case is not short commands, but long-form prompts: describing a bug, explaining desired refactors, writing issue reproduction steps, or drafting PR notes. Voice is excellent for that, but only if the transcript is safe to review before Enter.
A few UX notes from that direction:
MyVoiceTyping is early, but the related post-ASR polishing model and dataset are public if useful as references for the cleanup layer after transcription:
Voice input is available today. Run
/voicein the CLI to enable dictation, then hold the push-to-talk key (space by default, rebindable inkeybindings.json) while you speak, or switch to tap-to-record mode. The transcript lands in the prompt box so you can edit before sending. The VS Code extension supports it as well. It requires signing in with a Claude.ai account, and transcription runs on Anthropic's servers rather than locally. Docs: https://code.claude.com/docs/en/voice-dictation🤖 Generated with Claude Code