Official documentation
OpenLess README (Open-Less/openless)
OpenLess, GitHub repository Open-Less/openless, 2026
Read the originalRead on October 19, 2026
- What it is
- The README of OpenLess, an open-source voice input app for macOS, Windows and Linux, published by its maintainers in the project's own repository. It lists the speech recognition and AI polish providers and states how data is kept.
- How much weight it carries
- The project's own documentation, read in October 2026. A README describes intended behavior and can lag the code; the app's cloud providers are chosen by each user.
Facts taken from this source
- OpenLess's README says its text is AI-polished as it streams to the cursor.
“watch AI-polished text stream straight to your cursor” (README introduction)
- OpenLess's README says all of your data stays on your machine.
“all of your data stays on your machine” (README, "Why OpenLess is open source")
- OpenLess's README says proper nouns go into its dictionary as hotwords.
“Proper nouns sediment into dictionary hotwords” (README, Defaults section)
- OpenLess's README says it inserts the result at the cursor.
“and inserts the result at the cursor” (README introduction)
- OpenLess's README says it bundles the Qwen3-ASR local speech model for macOS.
“Local ASR : bundled Qwen3-ASR (0.6B / 1.7B) via vendored Open-Less/qwen-asr (macOS)” (README, Status section, "Local ASR")
- OpenLess's README lists OpenAI and Google Gemini among its polish providers.
“Polish providers : Ark (Volcengine), DeepSeek, OpenAI, Google Gemini” (README, Status section, "Polish providers")