| What it does | AI dictation for Windows in 50+ languages with privacy-first content handling
| Codebase intelligence platform for AI agents and teams
|
|---|
| Stage | Not given
| Startup
|
|---|
| Founded | Not given
| 2024
|
|---|
| Based in | PL
| Not given
|
|---|
| Pricing model | Freemium
| Freemium
|
|---|
| Pricing | Free: 10 dictations per day, each under 2 minutes. Monthly: $7.90/mo. Yearly: $69.90/yr (saves 26% vs monthly).
| Free: 2 public repos, 10 AI answers/month. Pro: $15/month (moving to $20/month in November, or $16/month yearly), includes private repos, auto-sync on every push, security scanning, $5/month AI credits. Teams: $20/seat/month with 3-seat minimum, includes 25 shared repos, shared $5/seat/month credit
|
|---|
| Key features | - Converts speech to polished, grammar-corrected text across 50+ languages
- Oral Backspace: correct yourself mid-sentence and automatically removes false starts
- Studio-Grade Noise Isolation for noisy or open office environments
- Memory-only audio processing with no recordings saved to disk
- Direct pasting at cursor into any Windows app with text input
- Ghost Mode: real-time translation from one language to another
- Global hotkeys and floating Mini Controller for hands-free access
- Compatible with AI coding tools and code editors
- Works with popular apps: VS Code, Slack, Notion, Gmail, Teams, ChatGPT, Claude, Gemini
| - Code health scoring with defect prediction
- Blast radius and change impact detection
- Auto-generated documentation rebuilt on every commit
- Git intelligence: hotspots, owners and coupling detection
- Architecture and decision tracking
- MCP tools for Claude Code and Cursor
- PR bot with change review and test detection
- Security scanning: CVEs, secrets and reachability
- Dead code detection and unused exports
- Change Records with policy enforcement
|
|---|
| What makes it different | - 3.5× faster than typing with speech input at 120-150 words per minute
- Privacy by design: audio never saved to disk, designed without content archive
- Built specifically for multilingual professionals and Windows workflow
| - Open source under AGPL-3.0, self-hostable with no LLM calls required to build the index
- Every published benchmark includes sample size, corpus and statistical methods
- Code health scores trained on years of real commits and defect fixes, with 0.74 AUC prediction accuracy
- Eliminates need to switch tools: integrates with Claude Code, Cursor, VS Code, GitHub and team dashboards
|
|---|
| 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) | Not checked yet ● no change since last check | 10 ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 8 |
|---|
| Citation Flow (Majestic) | 11 | 34 |
|---|
| Referring domains (Majestic) | 6 | 244 |
|---|
Typeglot
Repowise