DictatorFlow
Native voice dictation software that converts speech to text for writing, editing, and document work
The product is native voice dictation software that converts speech to text for writing, editing, and document work without typing. It addresses slow manual input and latency or accuracy limits of existing transcription tools. It is for individual consumers on desktop and for developers integrating speech-to-text via API. It is positioned as faster and more accurate than major providers on benchmarks, with local offline inference and optional cloud processing.
Key features
- Native voice dictation for desktop
- Local offline inference on device
- Optional cloud transcription
- 99+ languages with auto detection
- 150ms real-time latency
- 1.2% word error rate
- Edit text with voice commands
- Browser widget for textarea dictation
- REST API and WebSockets
- Multi-provider fallback chain
- PCM WAV WebM MP3 OGG support
- Live waveform overlay
- Language games and pronunciation practice
Social posts
- No social media activity within the last 30 days
GTM channels
- Blog
- Affiliate program
- API
- Docs
- Changelog
ICP
- Consumers general
- Software developers
- Freelancers solopreneurs