← Back (Home)

Telephone

project large language models machine translation

An LLM chat where every reply is translated by bad machine translation several times before you are able to read it.

? ? ?

Each reply from the model is translated through several languages (controlled by the button) then back to English. The translation is done by quantized Opus-MT models running locally in your browser, either on WebGPU or WASM. Each language automatically downloads around 100 megabytes on first use, which is then cached by your browser.

Using this tool requires entering an OpenRouter API key, and optionally a model slug if you do not want to use GPT-5.6-Luna. This key is not sent anywhere except OpenRouter, and it is not stored or cached in any way by me.

LLM-readable markdown version of this page