Blog
Articles on speech recognition, AI text refinement, developer workflows, and product updates.
Getting Started with Voice Coding: A Practical Guide to Ummless
A step-by-step tutorial for setting up Ummless on macOS — from installation and first recording to choosing presets and tips for dictation accuracy.
9 min read · tutorials
speech-to-textHow Speech-to-Text Models Are Trained: From Raw Audio to Accurate Transcription
Explore how modern ASR models like Whisper are trained — from data collection and preprocessing to model architecture, training, and evaluation metrics.
7 min read · speech-to-text
ai-refinementUnderstanding AI Text Refinement: How Raw Transcripts Become Polished Text
Learn how AI text refinement transforms messy speech transcripts into clean, professional text — the pipeline, presets, and why raw dictation is not enough.
9 min read · ai-refinement
developer-productivityVoice-to-Text Workflow for Developers: Dictate More, Type Less
Learn how developers can integrate voice-to-text into daily workflows — from commit messages and docs to code reviews and Slack, while reducing RSI risk.
8 min read · developer-productivity
privacyWhy Local Speech Recognition Matters: Privacy, Speed, and Independence
Discover why on-device speech recognition is the future — from data privacy and lower latency to offline capability and freedom from cloud dependencies.
7 min read · privacy