| What it does | Free voice-to-text app for developers that transcribes audio, translates languages, and integrates directly with Git workflows
| Persistent memory for AI coding agents that persists across sessions and tools
|
|---|
| Stage | Not given
| MVP
|
|---|
| Founded | Not given
| 2026
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Free trial
|
|---|
| Pricing | Starter: Free forever. Pro: $4/month (or yearly with 17% savings). Early Supporter: $99 one-time for lifetime access with all Pro features.
| Early access, enabled per company while onboarding founding teams. 50 free credits on signup, no credit card required.
|
|---|
| Key features | - Local offline Whisper speech models (Nano to Large V3 Turbo) with one-click switching
- Real-time translation across 90+ languages
- Git context integration with automatic PR and commit linking
- Voice-to-Knowledge Engine reconciliation with living documentation
- Multi-vault sync to Obsidian, Notion, Confluence, GitHub, Linear
- Audio and video file transcription with batch processing
- Text-to-speech synthesis with Kokoro and Silero local neural engines
- Support for 400+ local and cloud language models including Claude, GPT, DeepSeek
- Metal GPU acceleration on Mac and AVX2 CPU optimization on Windows
| - Preferences injected into every session on every AI coding tool
- Three scopes: personal, project, and company
- Auditable receipt for every memory injection
- Owner-editable and hard-deletable memories on demand
- Import from existing ChatGPT or Claude exports
- Engineering and general modes for non-engineering teams
- Works with Claude Code, Cursor, Codex and Grok Build
- Private stays private, every serve leaves a receipt
- Memories filtered per scope, not hidden in UI
- No credit card required to start
|
|---|
| What makes it different | - Cross-platform native app for both macOS and Windows with hardware acceleration
- Complete offline operation with zero audio retention or external server dependency
- Modular design allowing swapping of any speech recognizer and language model without vendor lock-in
- Living documentation engine that reconciles voice input with Git diffs to prevent decay
| - Solves the hidden tax of repeating the same instructions to AI agents every session
- Keeps personal preferences private while maintaining team and company policies
- Reduces context window token usage by 2.7x compared to raw history
- Immediate deletion with bodyless receipts for audit compliance
- Attached to you, not to a vendor's session store
|
|---|
| 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) | 1 ● no change since last check | 3 ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 4 |
|---|
| Citation Flow (Majestic) | 23 | 22 |
|---|
| Referring domains (Majestic) | 14 | 40 |
|---|
Dicty
Decispher Memory