| What it does | The voice layer for coding agents
| On-device voice AI SDK with no cloud dependency
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| CY
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: $0/month (open source with local voices). Pro: $12/month or $144/year (managed voices and spoken recaps). Power: $24/month or $288/year (adds voice input and iPhone companion). Every download includes a free 14-day Power trial with no card required.
| Published models free for commercial use; custom models available as paid engagements.
|
|---|
| Key features | - Spoken updates from Claude Code and Codex
- Three listening modes: Co-pilot, Companion and Focus
- Spoken recaps of agent work
- Voice dictation with right Command key
- Hey Parrot voice assistant
- iPhone companion app for listening and replying
- Follow multiple agent sessions at once
- Open source engine with local voices
- Works with any terminal including iTerm2 and tmux
- Up to 2M characters of narration daily on Power plan
| - Custom wake word detection with configurable threshold
- Streaming and batch automatic speech recognition
- Custom keyword spotting for voice commands
- Voice activity detection to identify speech
- Speech-to-intent with end-to-end processing
- Production binaries under 1 megabyte
- Models encrypted at rest with offline-first design
- NEON-accelerated battery-aware kernels
- Domain-specific model tuning
|
|---|
| What makes it different | - Works without watching your screen—lets you stay informed while focused on other tasks
- All code and transcripts stay on your Mac; nothing is used to train models
- Listen and respond to agents from your iPhone via companion app
- Open source engine available under Apache 2.0 license
- Supports multiple coding agents with one interface
| - Runs entirely on device with no cloud round-trip or per-detection fees
- Published models free for commercial use with custom tuning available
- Lightweight runtime under 1 MB with predictable latency and battery efficiency
- Models designed and tuned specifically to your product domain
- Audio never leaves the device and models are encrypted at rest
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 8 ▲ +2 (up) since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 3 |
|---|
| Citation Flow (Majestic) | 30 | 21 |
|---|
| Referring domains (Majestic) | 101 | 17 |
|---|
Heard
VoxRT