I’ve been using tools like ChatGPT for rewriting and Grammarly for grammar and tone checks, but over time they started to feel expensive for what I actually needed. What I really wanted was a simple way to catch toxic or overly aggressive messages before sending them, especially in real-time.

That’s what led me to build Convosify and launch it as an open beta on macOS. I’d love for you to try it out, and I’m very open to feedback and feature requests from the community.

Convosify is an offline-first conversation assistant that detects toxic language in real-time. Its built-in local ML/AI model checks your message instantly before sending the moment you hit “Enter”, and warns you before sending content that may be offensive, aggressive, emotionally harmful, accusatory, and cold tones. Detects nuanced emotions like disappointment, annoyance, and disapproval with sensitivity settings which users can dial in exact sensitivity levels.

Convosify offers advanced text enhancement capabilities, enabling you to rephrase, clarify, and refine your communication style. Profiling, and Custom Prompts.

Built for bilingual users, students, and teams who care about respectful, safe communication.

Open beta launch in MacOS at https://www.convosify.com

Convosify

Privacy-first AI conversation assistant.

Privacy-first AI conversation assistant.