Literal translation tools give you one answer. That answer has no register, no cultural context, and no way to know whether you're being warm or clinical.

I was writing a message to my girlfriend in Farsi — something small, about missing her during the day — and every tool I tried handed me back a single string with no indication of whether it would land tender or transactional. Native speakers don't think in one-answer phrases. They pick from a register range depending on who they're talking to and what they want to convey.

So I built konid: it returns 3 options per query, ordered casual to formal, with the register of each one explained and a cultural note comparing them. It also plays audio pronunciation through your speakers via node-edge-tts — no external API key, no browser tab, just audio.

The MCP setup is one line:

claude mcp add konid-ai -- npx -y konid-ai

Works in Claude Code, Cursor, VS Code Copilot, Windsurf, Zed, JetBrains, and Claude Cowork. Also installs as a ChatGPT app via Developer mode at https://konid.fly.dev/mcp.

Supports 13+ languages: Mandarin, Japanese, Korean, Spanish, French, German, Portuguese, Italian, Russian, Arabic, Hindi, Farsi, and more.

The name is Farsi — كنيد means "do." MIT licensed.

github.com/robertnowell/konid-language-learning