| What it does | Free AI dictation for Mac, Windows, Linux and iPhone that works offline
| A harness-agnostic framework for AI coding tools
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2025
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Free: Local Whisper and Parakeet models with unlimited offline use, bring your own API keys. Local+ $29 one-time purchase adds Notch and Capsule recording styles, settings sync, priority support. Pro $8.33/month (billed $99.99/year) or $9.99/month adds cloud models and AI text cleanup. Team plan $6.
| Not given
|
|---|
| Key features | - Supports 100+ languages with automatic detection
- Free local Whisper and Parakeet models for offline transcription
- Works in any application that accepts text input
- Real-time streaming transcription as you speak
- AI text cleanup with grammar and formatting
- Searchable dictation history with audio replay
- Bring your own API keys from OpenAI, Deepgram, Groq and others
- Claude Code and MCP server integration for AI agents
- Agent Mode for voice-controlled macOS automation
- Meeting recording and transcription on Mac
| - Configure plugins, skills, MCP servers, and hooks in a single harness.yaml file
- Observatory: monitor every session, tool call, and minute of activity
- Memory: persistent knowledge graph for AI orientation
- Comparator: run prompts across Claude Code, Cursor, and Copilot side by side
- Import existing configs from multiple AI coding tools automatically
- Share complete setup via single file with teammates
- Harness Parity: verify all connected AI tools end up with identical configuration
- Cross-harness compatibility table showing actual tool capabilities
|
|---|
| What makes it different | - Completely free offline dictation with local AI models, no account or payment required
- Works private and offline with voice never leaving your device
- Better than native Mac dictation with modern AI models handling technical terms and accents
- System-wide voice input across all applications without per-app installation
- 100,000+ active users with 4.8 App Store rating from 2,000+ reviews
| - Import-first approach: reads existing configs from all your tools and converges them before you write YAML
- No marketing gloss: capability table generated at build time from actual adapter code, not hand-maintained
- Portable across tools: single harness.yaml travels with you to every machine and tool
- Open source and free: no cost beyond existing Claude subscription
- Based on open specification: Harness Protocol is vendor-neutral and JSON Schema validated
|
|---|
| 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) | 57 ▲ +1 (up) since last check | 16 ● no change since last check |
|---|
| Trust Flow (Majestic) | 9 | 0 |
|---|
| Citation Flow (Majestic) | 38 | 20 |
|---|
| Referring domains (Majestic) | 520 | 11 |
|---|
Spokenly
Harness Kit