Feature request: JARVIS-style voice-to-voice hands-free mode for Claude Code

Status Closed — not planned
Maintainer reply None cached
Activity 5 comments · opened Apr 19, 2026 · closed Jun 8, 2026

Problem / use case

I run a field-service CRM project (HVAC dispatcher, 903+ clients, 2 crews). I spend a lot of my working time away from my desk — driving between sites, walking around, hands full. My laptop stays at home and I connect to Claude Code via Remote Desktop from my iPhone, wearing AirPods.

Right now the workflow on the phone is painful:

  • I have to tap the mic on the iOS keyboard to dictate
  • Then tap the send button
  • Then read Claude's response by hand — or swipe twice with two fingers to trigger iOS "Speak Screen"
  • Then tap mic again
  • ...repeat

What I actually want is a continuous voice-to-voice conversation — the same experience ChatGPT Advanced Voice Mode / "JARVIS" gives you. I talk, pause, Claude Code hears me, reasons, answers out loud, I can interrupt, I answer back, no taps in between.

The closest thing today is the Claude mobile app Voice Mode, but that app doesn't see my project files / git / codebase — so it can't actually help me ship features. Claude Code can ship features but has no voice layer at all.

Proposed feature

A built-in Voice Mode in Claude Code:

  • Toggleable per session: /voice on or a dedicated hotkey
  • Uses a realtime STT → model → TTS pipeline (Anthropic-hosted, ideally using Claude with native audio I/O if/when available)
  • Continuous listening with barge-in (interrupt the assistant mid-sentence)
  • Streams Claude's response to TTS so the user hears it as it's generated, not after
  • For tool calls and long file operations, speaks a short status ("reading calendar-settings.ts, running typecheck…") so the user knows work is happening
  • Keeps the full text transcript visible in the terminal / web UI exactly as today — voice is additive, not replacing
  • Works in the web session too (claude.ai/code/session_…) so remote-desktop / mobile use-cases work

Why this is specifically valuable in Claude Code (not just chat)

Developers and small-business operators like me aren't only coding. We're reasoning about real work while in motion — triage, planning, reviewing what an agent did, deciding what to build next. Today I have to choose: tap-typing a complex instruction on a phone screen, or losing the project context by switching to the Claude chat app. A voice layer closes that gap.

Languages

Please make sure non-English locales are first-class — in my case Russian. Both STT and TTS should respect system locale / a --voice-lang flag.

Not what I'm asking for

  • Not "transcribe my dictation and paste it" — that exists everywhere
  • Not "read the last message aloud on command" — iOS Speak Screen already does that
  • What's missing is the continuous loop with barge-in

Alternatives considered

  • iOS Shortcuts → Claude Code CLI over SSH: fragile, can't barge in, no streaming
  • Custom pipeline with Whisper + Anthropic API + ElevenLabs: doable but out of scope for 99% of users, and loses the Claude Code tooling (git, file ops, hooks)
  • ChatGPT Advanced Voice Mode: great voice UX, no access to my project / files / codebase

Would love to see this land. Happy to beta-test on Russian + a real CRM codebase.

Thanks!

View original on GitHub ↗

5 Comments

derekhaugen · 4 months ago

I would use this feature as well.

ericvegasdev-spec · 3 months ago

Saw your hands-free Claude Code feature request. The HVAC dispatcher use case rang loud. Tap-mic, tap-send, Speak Screen, repeat is the exact friction loop that kills mobile Claude usage for field operators. I already built a productized voice-to-voice loop that runs through Siri and iMessage with your AirPods, no tapping. Want to see how it works? remote-claude.com

mbailey · 3 months ago

I've been using VoiceMode for this exact purpose for almost a year now.

  • Makes Hands / Screen optional when working with Claude Code
  • Free and Open Source
  • Installs local voice services: Privacy, Cost, Latency, Bandwidth
  • Works with any MCP client

https://github.com/mbailey/voicemode

github-actions[bot] · 2 months ago

Closing for now — inactive for too long. Please open a new issue if this is still relevant.

davevasc · 13 days ago

Adding what I think is the missing piece for true JARVIS-parity: screen sharing in voice mode (iOS and Android).

Right now, even with the improved voice mode (better models, no Haiku-only limit), there's no way to look at your screen and ask Claude about it while staying in voice — you have to break the flow and attach a screenshot manually. ChatGPT's Advanced Voice Mode has had on-demand screen sharing via ReplayKit since December 2024.

What would unlock the JARVIS experience:

  1. User is in voice mode
  2. Navigates to another app on the phone
  3. Says "look at my screen" or taps a button
  4. Claude sees a frame and responds in voice
  5. Never typing, never leaving the app

This would also fix two related bugs blocking the same use case today:

  • Image attachments ("+") silently fail in voice mode on iOS — they show as attached on screen but Claude never receives them
  • Using the iOS share sheet to attach a screenshot kills the active voice session and opens a new chat instead of attaching to the one already running

ChatGPT proved the platform allows this — it's not a technical barrier, it's a prioritization call. If Anthropic closes these gaps, voice mode becomes the standout feature of the iOS app instead of a half-finished one.

I've opened a detailed feature request specifically for this: #87294