
OCR - Image Reader is a Chrome extension from developer brian.girko that adds a toolbar button for on-the-fly optical character recognition. Press the button, drag a selection over any region of the active window, and the extension reads the text inside it using a Tesseract-based engine that supports over 100 languages with automatic orientation and script detection. A second engine option, IBM Granite-Docling, goes further and preserves headings, lists, bold and italic styles, tables and even mathematical equations instead of returning flat text. Everything runs offline in the browser, with no server round trips apart from a one-time download of the language training data.
| 维度 / 指标 | ![]() | |
|---|---|---|
| 官方域名 | janitorai.com | chromewebstore.google.com |
| 定价模式 | 免费增值 | 免费 |
| 月访问量 | 1.25亿 (125,494,484) | 0 (0) |
| 月度环比流量变化 | -677.05万 (-5.1%) | 0 (—) |
| 主要市场与份额 | 🇺🇸 美国 (38.7%) | 🌐 全球 (—) |
| 直接访问 / 月 | 8952.77万 | 0 |
| 用户评分 | 4.2 | 4.6 |
| 支持的平台 | 网站 | 浏览器扩展 |
可自定义的 AI 角色扮演平台,提供免费 JanitorLLM 聊天、逻辑脚本与多模型 API 路由。
提供由 JanitorAI 自有 LLM 驱动的无限免费角色聊天(免费账户约 9K 上下文窗口),并有可切换的 JLLM-short 模式,用于生成短约 70%、节奏更快的对话式回复。
让 Janitor+ 订阅者通过内置的按 token 钱包以 10% 折扣直接使用第三方前沿模型,同时保留完整的 BYOK 反向代理支持,并具备配置复制与推理标签显示。
允许创作者构建最大 1 MB 的复杂角色,包含多个开场情景,以及可用全词匹配和内置调试工具触发动态设定或行为规则的可编程 Scripts。
在聊天菜单中暴露底层采样参数,包括自定义 Top-K、Top-P、频率与重复惩罚、禁用词汇列表以及回复预填指令。

OCR - Image Reader is a Chrome extension from developer brian.girko that adds a toolbar button for on-the-fly optical character recognition. Press the button, drag a selection over any region of the active window, and the extension reads the text inside it using a Tesseract-based engine that supports over 100 languages with automatic orientation and script detection. A second engine option, IBM Granite-Docling, goes further and preserves headings, lists, bold and italic styles, tables and even mathematical equations instead of returning flat text. Everything runs offline in the browser, with no server round trips apart from a one-time download of the language training data.
Click the toolbar icon, draw a rectangle over any part of the active window, and the text inside is recognised immediately.
A Tesseract.js engine recognises plain text in over 100 languages with automatic text orientation and script detection.
Switch to IBM Granite-Docling to retain headings, lists, bold and italics, tables and mathematical equations instead of losing layout.
The OCR runs entirely in the browser with no server calls; only the language database is downloaded once and then cached.

Features massive user-generated persona libraries with voice playback for casual character chatting.

Combines adult-focused character chat, storytelling, and image generation for creative roleplay users.
Combines adult-focused character chat, storytelling, and image generation for creative roleplay users.

免费 / 开源Provides privacy-focused, uncensored open-source model APIs that advanced users can route for private roleplay.
免费 / 开源Provides privacy-focused, uncensored open-source model APIs that advanced users can route for private roleplay.
提供无限制的动漫与奇幻角色聊天,符合 JanitorAI 宽松的内容政策。
免费在线 OCR,一键把图片变成可编辑文字
Enables custom persona creation and open-ended roleplay adventures in a similar community environment.
An independent platform for custom character creation and open-ended roleplay sessions with minimal restrictions.
专项更强用 OCR 从图片、扫描件与手写体中提取可编辑文字
免费在线 OCR,将 JPG、PNG 和扫描图片转成可编辑文字