| What it does | Free voice-to-text app for developers that transcribes audio, translates languages, and integrates directly with Git workflows
| Fine-tuned small models for English-to-Bash command generation
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Freemium
| Open source
|
|---|
| Pricing | Starter: Free forever. Pro: $4/month (or yearly with 17% savings). Early Supporter: $99 one-time for lifetime access with all Pro features.
| Not given
|
|---|
| 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
| - 1.5B and 0.6B fine-tuned models
- 401,975 synthetic training examples
- 4-bit quantized models
- CLI with llama.cpp integration
- Command preview mode
- Covers file operations, text processing, Git, archives, networking
- Training data and checkpoints available
- Apache 2.0 and MIT licensed
- ALFA-updated benchmark evaluation
- Supervised fine-tuning with LoRA
|
|---|
| 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
| - 70.7% pass rate on ALFA-updated benchmark vs 63.7% for competing models
- CPU-friendly quantized models
- Specialized for bash command generation from natural language
- Agentically trained with synthetic data generation and evaluation
|
|---|
| 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 | 36 ● no change since last check |
|---|
| Trust Flow (Majestic) | 3 | 6 |
|---|
| Citation Flow (Majestic) | 23 | 32 |
|---|
| Referring domains (Majestic) | 14 | 219 |
|---|
Dicty