Vendor page
说点啥 BiBi Keyboard (homepage)
BryceWG, BiBi Keyboard, n.d.
Read the originalRead on October 19, 2026
- What it is
- The homepage of BiBi Keyboard, an Android voice input keyboard by BryceWG. It lists offline recognition with local models, a floating ball that works over any keyboard, LLM post-processing and voice-instruction editing, a free open-source edition and a Pro edition, and its data policy.
- How much weight it carries
- The maker's own page, in Chinese, read in October 2026. The data policy is stated by the maker; the page does not name a third-party privacy audit.
Facts taken from this source
- BiBi Keyboard's homepage says an LLM refines recognized text with punctuation, formatting and preset prompts.
“LLM 文本精修,自动标点、格式化,多场景预设提示词,让识别结果更完美” (AI smart post-processing)
- BiBi Keyboard's homepage lists unified hotword management in its Pro edition.
“繁体中文转换 正则后处理 统一热词管理 自动备份(WebDAV)” (Pro edition feature list)
- BiBi Keyboard's homepage says its open-source edition is completely free.
“选择适合你的版本 开源版 完全免费 · 开源” (Version comparison)
- BiBi Keyboard's FAQ says the app does not upload audio itself and keeps no copy of it.
“当你启用云端 ASR 或 AI 后处理时,音频/文本会按你的设置加密传输至相应服务商;说点啥本身不额外上传,也不保留副本。” (FAQ: data collection)
- BiBi Keyboard's FAQ says it does not collect personal data and keeps settings and history on the device.
“我们不收集你的个人数据。 所有配置与历史仅保存在本地设备。” (FAQ: data collection)
- BiBi Keyboard's FAQ says audio and text go to the chosen provider when cloud ASR or AI post-processing is on.
“当你启用云端 ASR 或 AI 后处理时,音频/文本会按你的设置加密传输至相应服务商;说点啥本身不额外上传,也不保留副本。” (FAQ: data collection)
- BiBi Keyboard's homepage says its floating ball gives voice input on any keyboard and inserts text automatically.
“跨键盘悬浮球 无需切换输入法,任何键盘上都能使用语音输入,支持自动文本插入” (Feature list)
- BiBi Keyboard's homepage lists editing text by voice instruction as part of its LLM editing feature.
“集成 LLM 大语言模型,提供智能文本后处理和编辑功能: 自动添加标点和格式化 语音指令编辑文本” (AI smart editing)
- BiBi Keyboard's FAQ says offline recognition works with local models after they have been downloaded.
“是否支持离线识别? 支持!使用本地模型 SenseVoice/Paraformer/Funasr Nano 可实现完全离线识别。首次使用需先下载模型资源。” (FAQ)