DashVox
Hands-free AI for devs
Free · Designed for iPhone. Not verified for macOS.
Your voice-first AI engineer. Kick off remote coding sessions from CarPlay, Apple Watch, or headphones — and hear the result spoken the moment each one lands.
DashVox is a voice-first AI engineering assistant for when your hands aren't on a keyboard.
Commute, walk, bike, run, or just step out for coffee — DashVox lets you orchestrate real engineering work by voice. Kick off coding sessions on your dev machine, triage bug reports, review repos, draft release notes, or catch up on what happened while you were offline. The work runs remotely; DashVox keeps you in the loop and hands you a clean spoken summary when each task lands.
WHAT YOU CAN DO
• Spin up AI coding sessions on any SSH-reachable machine by voice. Your preferred coding agent handles the actual work on the remote end.
• Keep the conversation going while sessions run in the background. Queue follow-ups, pivot to other topics, or just listen — DashVox surfaces each completion automatically when it's ready.
• Run multiple sessions in parallel. The app batches completions cleanly so several finishing at once doesn't overwhelm you.
• Ask general questions with built-in web search for current information.
• Drop into raw shell mode when you need an unwrapped terminal command.
• Every spoken reply is shaped for audio: plain prose, no emojis, no markdown noise, no JSON read aloud.
MEET YOU WHERE YOU ARE
• CarPlay: full chat and session experience on your vehicle's display — hands on the wheel, eyes on the road.
• Apple Watch: spoken updates and quick status checks from your wrist. Take a call, take a walk, take a run — your background agents keep working.
• iPhone + AirPods: voice input and audio-first output for errands, transit, the grocery line, or anywhere you'd rather listen than look.
BRING YOUR OWN INFRASTRUCTURE
• DashVox Cloud works out of the box. Prefer self-hosted? Point the app at your own backend and run the whole stack on your hardware.
• SSH directly to your dev box over Tailscale, VPN, or the public internet. Direct-client mode skips the backend entirely for the lowest possible latency.
• Bring your own agent: Claude Code, Claude Cowork, Codex, or any custom CLI. Agent profiles let you tune flags, session flags, and working directories per machine.
• Password or private-key SSH auth, stored in the iOS keychain.
WHY IT'S DIFFERENT
• Non-blocking by design. Start a task, get the session id back instantly, and keep talking. When the remote agent finishes — minutes or hours later — DashVox tells you.
• Burst-safe. Three sessions landing in five seconds? You get one clean summary, not three interruptions.
• Audio-first. No visual noise. No JSON. No markdown tables read letter-by-letter. Every response is written for ears.
PRIVACY AND CONTROL
• Self-hosted is a first-class mode, not an afterthought. Run your own backend, keep conversations and sessions on your hardware.
• SSH credentials stored in the iOS keychain, never synced to any cloud we control.
• No ads. No tracking. No training on your prompts.
WHO IT'S FOR
• Software engineers who spend time away from a keyboard
• Commuters, walkers, runners, cyclists, and anyone who'd rather listen to work happen than stare at a screen
• Founders and tech leads who want continuity between the office and everywhere else
Ratings & Reviews
- Fixed: CarPlay voice replies could go silent mid-drive and never recover. When a navigation app (e.g. Google Maps) spoke a turn-by-turn prompt, it interrupted the audio session and left text-to-speech stuck — after that, nothing was read aloud,
including "Read Last Response." TTS now detects these interruptions and automatically restores itself, so replies keep reading the whole drive. - Added: a "message sent" sound so you get audible confirmation your dictated message went through without looking at the screen. - Added: a "Last reply" row at the top of the CarPlay chat screen showing the agent's most recent reply as text — a glanceable backup for when audio is interrupted. Tap it to hear the reply again (this also re-arms TTS if it was interrupted).
- Improved: more resilient audio handling under heavy navigation, with an automatic retry so TTS recovers cleanly instead of staying broken.
The developer, JACK ZANTE HAYS, indicated that the app’s privacy practices may include handling of data as described below. For more information, see the developer’s privacy policy .
Data Linked to You
The following data may be collected and linked to your identity:
- Contact Info
- User Content
- Identifiers
- Usage Data
Accessibility
The developer has not yet indicated which accessibility features this app supports. Learn More
Information
- Seller
- JACK ZANTE HAYS
- Size
- 33.1 MB
- Category
- Developer Tools
- Compatibility
Requires iOS 17.0 or later.
- iPhone
Requires iOS 17.0 or later. - Mac
Requires macOS 14.0 or later and a Mac with Apple M1 chip or later. - Apple Vision
Requires visionOS 1.0 or later. - Apple Watch
Requires watchOS 11.0 or later.
- iPhone
- Languages
- English
- Age Rating
4+
- 4+
- Copyright
- © 2026 Jack Zante Hays