| What it does | Push-to-talk voice input for coding with AI
| Autonomous AI coding agent with deterministic program repair
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | Not given
| ID
|
|---|
| Pricing model | Open source
| Freemium
|
|---|
| Pricing | Free, open source (AGPL-3.0-only)
| Core Basic: free (20 CLI / 15 Web runs per day, 50K daily AST tokens). Apex Pro: $11/month (100 CLI / 75 Web runs per day, 250K daily AST tokens). Sovereign Ultra: $44/month (400 CLI / 300 Web runs per day, 1.0M daily AST tokens). Annual subscriptions include 2 months free.
|
|---|
| Key features | - 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
| - 4.1µs C-ABI latency native Rust Sub-Cortex execution
- Zero dirty diffs with strict AST grammar validation and dry-run verification
- Support for 6 production languages: Python, Rust, TypeScript/JavaScript, Go, C/C++, and Java
- Polyglot language engines with direct Tree-sitter CST surgery
- Machine-to-Machine sub-cortex infrastructure for autonomous agents
- Zero Code Retention policy with ephemeral in-memory processing
- 91.3% AST token pruning for repository context efficiency
- Multi-file repository context with automated test-runner verification
- Automated 5-Whys Root Cause Analysis and SRE incident diagnostics
- System-wide dependency mapping and security audit capabilities
|
|---|
| What makes it different | - 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
| - Eliminates 95% of LLM token overhead through deterministic compiler verification instead of probabilistic inference loops
- Operates locally with strict Zero Code Retention policy—no code logging, storage, or model training usage
- Sub-microsecond repairs in CPU L1 cache without garbage collection pauses via native Rust FFI
- Engineered as M2M sub-cortex infrastructure for autonomous agents, not consumer chatbot utility
|
|---|
| 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 ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 4 | 0 |
|---|
| Citation Flow (Majestic) | 21 | 15 |
|---|
| Referring domains (Majestic) | 48 | 2 |
|---|
VocalCode
Kronumos