OpenLess
Open-source cross-platform voice input tool that supports macOS, Windows and Linux. Press the hotkey and speak to transcribe locally and polish into clean text or structured prompts. Released under MIT License, with data local-first.
Updated: 2026-10-26
What is OpenLess?
OpenLess is an open-source, local-first voice input tool that covers macOS, Windows, and Linux, licensed under the MIT License. It has a restrained positioning: press the hotkey, speak, and get polished and clean text at the cursor. The official states that the model only organizes your words and will not answer for you; compared with closed-source subscription products such as Typeless and Wispr Flow, the code, data, and credentials all remain on your own device.
Who is it for?
- Developers and power users who interact with ChatGPT, Claude, and Cursor on a daily basis and frequently write Prompts.
- People who need to write a lot of text but type slowly or are reluctant to type, such as dictating emails and documents.
- Users who value privacy and do not want their voice data to pass through third-party closed-source services.
- Open-source enthusiasts who want to modify the code themselves and integrate their chosen ASR and model services.
Key features
5Hotkey Voice Input
Compatible with any input box with a cursor. Officially stated to support applications such as ChatGPT, Claude, Cursor, Notion, Slack, WeChat, and email.
Local-first storage
The official states that audio files, transcriptions, dictionaries, and history are all stored locally; credentials are saved in the Keychain, and configurations are stored in the ~/.openless directory, with no data leaving your local machine.
Bring Your Own Cloud (BYO)
Integrates with Volcengine Streaming ASR and Ark/DeepSeek-compatible chat-completions APIs. The official states that you can switch providers and are not locked into any single one.
Prompt Polishing
Dictate a requirement, get a structured Prompt with context, constraints and specifications, only organizing content without providing answers on your behalf.
Fully open-source and transparent
Licensed under MIT, the hotkey listener, AVAudioEngine, AX injection, and Prompt templates are all publicly available with no black boxes.
How to use OpenLess
- Get started in three steps: Select the installation package according to the platform (the DMG for macOS is divided into Apple Silicon and Intel, x64-setup.exe for Windows, and AppImage, deb, rpm for Linux), grant microphone and input permissions after completing the installation.
- macOS users also need to grant accessibility permissions and restart OpenLess after authorization.
- the official note indicates that it is currently ad-hoc signed, so quarantine needs to be lifted for the first launch, which can be done by following the documentation.
- The transcription and polishing effects depend on the ASR and model you connect to.
- It is recommended to first test several common phrases with your self-selected DeepSeek-compatible service and then fix them.
- Download the latest stable version from GitHub Releases, follow the MIT License, and check the official Changelog for version changes.
Traffic & popularity
Data month Sep 2026
OpenLess receives about 5.0K visits per month and ranks #3,034,099 worldwide.
Monthly visits
8 monthsTraffic sources
- Direct40.8%
- Search33.6%
- Referrals11.9%
- Social6.1%
- Mail2.3%
- Other5.3%
Top countries
- Taiwan, China87.7%
- United States12.3%
Estimated from third-party traffic data.
Similar tools
SayItOpen-source voice input tool for Windows: Press the shortcut key and speak, then the AI removes filler words and organizes the content according to custom prompt words, directly inputting it into Claude Code, Codex, Kiro, or any inputable area.
ApplioApplio is an open-source and free AI voice conversion suite that can convert audio into any timbre, perform real-time voice changing, support training timbre models with your own data, and run locally without an account. It is suitable for creators who do covers, live broadcast voice changing and dubbing.
SuperWhisperSuperWhisper is a cross-platform speech dictation tool. You can speak in any application to get polished text. It supports over 100 languages, offline transcription and automatic meeting recording, and is suitable for writing, programming and daily office input.
UnmuteThe voice interaction project Unmute launched by Kyutai is officially described as "enabling large language models to listen and speak", with the goal of endowing LLMs with real-time auditory and speech capabilities; its official website is a dynamically loaded page with limited publicly visible details.
JoyCastA tool for real-time noise reduction and voice enhancement of MacBook microphones. The official claims it can remove up to 97% of background noise with a delay of about 20ms. It runs entirely locally without uploading to the cloud, and it takes effect as soon as you switch the input to JoyCast Mic.
VoiceboxAn open-source local voice studio that clones timbre from a few recordings, generates speech across multiple TTS engines, and enables global dictation in any application. The official description states that it is a free local alternative to ElevenLabs and WisprFlow.