| What it does | Push-to-talk voice bridge between AI coding agents and two-way radios
| Push-to-talk voice input for coding with AI
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Paid
| Open source
|
|---|
| Pricing | Lifetime license (one-time payment, price not shown; excludes tax, added at checkout)
| Free, open source (AGPL-3.0-only)
|
|---|
| Key features | - Whisper speech recognition in Turkish and English
- Neural voice synthesis with Kokoro and EMA models on CoreML
- VOX wake tones and roger beep
- Target Window mode types into Cursor, Antigravity, Terminal or any app
- API Mode connects to OpenAI, Anthropic, Gemini, DeepSeek, or Ollama
- Local API on port 127.0.0.1:1988 for any agent
- Offline operation for up to 14 days between license checks
- Command history with playback and timestamps
- Noise guard filters low-frequency rumble and desk thumps
- Automatic input level balancing to prevent clipping
| - Push-to-talk dictation in most desktop applications
- On-device speech recognition with no audio uploaded
- Works offline after model download
- Support for 29 languages including 25 European languages, Mandarin Chinese, Hindi, Korean and Japanese
- Local meeting recording, transcription and evidence-linked notes
- Rebindable push-to-talk hotkeys for Windows and macOS
- Text insertion into active field in most desktop applications
- Free and open-source desktop app under AGPL-3.0-only
|
|---|
| What makes it different | - Works completely offline; speech recognition and neural voice synthesis run locally on your Mac
- Supports any VOX-enabled two-way radio with a simple audio cable
- Lifetime license for one Mac; move to a new Mac whenever you want
- No subscription, one-time payment covers all updates forever
- Accessible automation types commands via macOS Accessibility, even away from the keyboard
| - Speech recognition runs entirely on your own machine with no audio or transcript uploaded
- Works completely offline after initial model download
- Completely free and open source with no payment, account or activation required
- Types directly into active application without copying from dictation box
- Supports 29 languages with multiple on-device recognition models
|
|---|
| 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) | 6 ● no change since last check | 8 ● no change since last check |
|---|
| Trust Flow (Majestic) | 15 | 4 |
|---|
| Citation Flow (Majestic) | 22 | 21 |
|---|
| Referring domains (Majestic) | 20 | 48 |
|---|
walkai-talkai
VocalCode