openless: an open-source voice-to-text utility that polishes spoken input into structured AI prompts and professional text
openless: an open-source voice-to-text utility that polishes spoken input into structured AI prompts and professional text
What it solves
OpenLess is a cross-platform voice-input application that eliminates the friction between spoken thoughts and clean, usable text. Unlike standard dictation tools that provide literal word-for-word transcripts, OpenLess uses AI to polish, structure, and format spoken input into professional text or detailed AI prompts, inserting them directly at the user's cursor in any application.
How it works
The application operates as a system-wide utility on macOS and Windows. Users hold a global hotkey, speak their thoughts, and release the key. The system then follows a pipeline: speech is captured and sent to an ASR (Automatic Speech Recognition) engine (supporting both cloud providers like Volcengine and local models like Qwen3-ASR), transcribed, and then processed by a Large Language Model (LLM) to polish the text based on a selected style. The final result is streamed character-by-character into the active text field.
Who it’s for
- AI Power Users: People who want to compose complex prompts for LLMs (ChatGPT, Claude, Cursor) by speaking rather than typing.
- Content Creators: Those drafting emails, specifications, or social media posts who want to remove filler words and organize thoughts quickly.
- Developers: Users needing to capture code comments, commit messages, or PR descriptions without leaving their IDE.
Highlights
- AI-Prompt Mode: Specifically designed to turn loose speech into structured prompts with context and constraints.
- Style Pack Marketplace: A community-driven system where users can install or publish custom system prompts to change the output tone and format.
- Streaming Insertion: Reduces perceived latency by flowing text into the cursor in real-time as it is polished.
- BYO-Model: Supports bring-your-own cloud credentials (DeepSeek, OpenAI, Anthropic, etc.) and local ASR models to ensure data privacy and avoid vendor lock-in.
- Cross-Platform: Native support for macOS and Windows using a Tauri/Rust backend.
Sources
- undefinedOpen-Less/openless