WordBot - AI Text Tools

AI text tools via right-click: correct, translate, fact-check, generate. Supports GPT, Claude, Gemini & custom endpoints.

Select any text on any webpage, right-click, and instantly correct, translate, fact-check, or generate content — powered by the AI model of your choice. What it does • Correct — Fix spelling, grammar, and missing diacritics. See changes as an inline diff with additions and removals highlighted. • Translate — Translate selected text into 45+ languages. Pick your target language from a quick dropdown. • Fact Check — Analyze selected text for factual accuracy. Get verdicts (true, false, misleading, unverifiable) for each claim. • Generate — Summarize, simplify, expand, explain, convert to checklist, or refactor code. Nine modes across three categories. How it works Select text on any webpage Right-click → WordBot → pick an action Results appear in a floating popup right next to your selection Bring your own API key WordBot connects directly to the AI provider you choose — no middleman, no proxy server. Your text goes straight from your browser to the API. Supported providers and models: • OpenAI — GPT-4.1 Nano, GPT-4.1 Mini, o3-mini • Anthropic — Claude Haiku 4.5 • Google Gemini — Gemini 2.5 Flash-Lite, Gemini 2.5 Flash • Custom — Any OpenAI-compatible endpoint (company-internal LLMs, Ollama, LM Studio, vLLM, LocalAI, LiteLLM) Usage tracking Built-in token counter and cost estimator so you always know what you're spending. View per-model breakdowns and reset anytime. Privacy • API keys stored locally in your browser profile • No intermediary servers — text goes directly to your chosen AI provider • No analytics, telemetry, or third-party data collection Changelog — v1.1.0 (April 2026) • Added Custom (OpenAI-compatible) provider for self-hosted and company-internal LLMs • Replaced deprecated Gemini 2.0 Flash with Gemini 2.5 Flash-Lite and Gemini 2.5 Flash • Replaced deprecated GPT-4o Mini with GPT-4.1 Mini • API keys are now stored per-provider — switching providers no longer loses your key • Improved compatibility with thinking models (Qwen, DeepSeek, etc.) • Updated pricing