[← Back (Home)](/)

# Telephone

July 30, 2026 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.

openrouter key model (optional)

languages ▾ corrupt the model's memory ? sanity ? supersanity ? reset chat

send

Each reply from the model is translated through several languages (controlled by the languages ▾ 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](/projects/telephone/llms.txt)