| What it does | Push-to-talk voice input for coding with AI
| Cut Claude Code, Codex & Gemini quota burn by 60–72% with persistent AI coding memory and deterministic verification
|
|---|
| Stage | Startup
| Not given
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | Not given
| RO
|
|---|
| Pricing model | Open source
| Freemium
|
|---|
| Pricing | Free, open source (AGPL-3.0-only)
| Explorer: free with 50 MCP calls; Oxyo Core: $19/mo (or $15/mo annually) with ~1.9M tokens/week and 300 MCP calls/week; Oxyo Pro: $49/mo (or $39/mo annually) with ~3.8M tokens/week and 1,250 MCP calls/week; Oxyo Max: $99/mo (or $79/mo annually) with ~7.5M tokens/week and 5,000 MCP calls/week. All pl
|
|---|
| 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
| - Lifelong persistent memory across sessions retained in an isolated vault
- Automatic belief revision to eliminate contradicted specifications
- Deterministic Python sandbox for verified calculations
- Model Context Protocol integration for IDE connectivity
- Causal root-cause graph tracking
- Visual learning from screenshots and diagrams
- Reusable skill synthesis for algorithmic classes
- Web console, desktop app, and REST API access
- Encrypted BYOK vault for Claude, OpenAI, and OpenRouter
|
|---|
| 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
| - 60–72% reduction in token quota burn measured on production 112k-token repositories
- Zero re-sending of context; only ~1k surgical tokens retrieved per turn instead of 50k–200k
- 100% contradiction-free memory with automatic outdated fact retirement
- Unified memory across web, browser, and multiple IDEs
- Model-independent brain; memory portable across AI providers
|
|---|
| 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 | 0 |
|---|
| Referring domains (Majestic) | 48 | 0 |
|---|
VocalCode
Oxyo