BiBi Keyboard

July 26, 2026 ยท View on GitHub

Logo

BiBi Keyboard

AI-powered Smart Voice Input Method | Make Voice Input More Natural and Efficient

๐ŸŒ Official Website โ€ข ๐Ÿ“– Documentation

English | ็ฎ€ไฝ“ไธญๆ–‡

License Platform Language Telegram zread Ask DeepWiki GitHub all releases

Features โ€ข UI Showcase โ€ข Quick Start

๐Ÿ“ฑ UI Showcase

BiBi Keyboard onboarding, voice keyboard, and smart settings
Easy Setup
Step-by-step guidance for IME and permission setup
Voice-first Typing
Open the keyboard and hold the microphone to speak
Smart Enhancements
Manage recognition, AI post-processing, and history

โœจ Features

๐ŸŽค Voice Recognition

  • Press & Hold Recording - Simple and intuitive recording
  • Smart Auto-Stop - Automatically stops recording on silence
  • Fast Recognition - Release to upload, quick results
  • Multi-Engine Support - 18 ASR vendors (12 cloud + 6 local)
  • Local ASR Models - SenseVoice / FunASR Nano / Qwen3-ASR / Parakeet / FireRedASR / X-ASR for offline use
  • Primary + Backup - Backup engines and local backup residency for unstable networks
  • AI Text Optimization - LLM post-processing; history can cache audio and re-run recognition/post-processing

๐ŸŸฃ Floating Ball Input โญ

  • Cross-IME Usage - Voice input with any input method
  • Hold to Record - Press and hold to record, release to stop
  • Seamless Integration - Maintain your original typing habits
  • Auto Insertion - Recognition results automatically inserted
  • Compatibility Mode - Support for Telegram, TikTok and other special apps
  • Visual Feedback - Recording/processing status at a glance

๐Ÿ“ Smart Input

  • AI Edit Panel - Dedicated editing interface with voice command text editing
  • Custom Keyboard Layout - Freely rearrange key pools and panels
  • Clipboard Sync & History - SyncClipboard upload/pull plus in-app clipboard history
  • IME Bridge - Record, commit text, and sync clipboard in third-party IMEs via LSPosed/LSPatch module
  • Fcitx5/Trime Integration - Invoke BiBi recognition from modified Fcitx5-Android/Trime
  • External Speech Input Interface - Third-party apps via SpeechRecognizer / AIDL Open-source Test Tool

๐ŸŽจ User Experience

  • Material3 / Miuix - Modern settings UI with Monet and Miuix styles
  • Multi-language Support - Simplified Chinese, Traditional Chinese, English, Japanese, and Arabic
  • Keyboard Height Adjustment - Three height levels to choose from
  • Auto Enter After ASR - Optionally send automatically after recognition in chat apps
  • Backup & Restore - One-tap export/import of settings
  • Vibration Feedback - Microphone / keyboard button vibration
  • Auto Update Check - Daily automatic update check on app launch

๐ŸŒŸ Pro Version Released

๐Ÿ’Ž BiBi Keyboard Pro is now officially available on the Play Store for a one-time purchase of just $5.49!

The Pro version offers more advanced features and a better experience (hotwords, Simplified/Traditional conversion, continuous dictation, WebDAV auto-backup, and more). You can learn more in About โ†’ Learn about Pro, or in the Pro Features documentation. We welcome your feedback to help us polish a better product!

If you are interested in BiBi Keyboard, join our Telegram Group for more information.

๐Ÿš€ Quick Start

Provider Configuration Guide

๐Ÿ“‹ System Requirements

  • Android 8.0 (API 26) or higher
  • Microphone permission (for voice recognition)
  • Overlay permission (optional, for floating ball feature)
  • Accessibility permission (optional, for automatic text insertion)
  • LSPosed / LSPatch (optional, for integration with any third-party IMEs)

๐Ÿ“ฅ Installation Steps

  1. Download & Install

    • Download the latest APK from Releases page
    • Install on your Android device
  2. Enable Input Method

    Settings โ†’ System โ†’ Language & Input โ†’ Virtual Keyboard โ†’ Manage Keyboards โ†’ Enable "BiBi Keyboard"
    
  3. Configure ASR Service

    • Open BiBi Keyboard settings
    • Select ASR vendor (recommended: Volcengine)
    • Enter your API key
  4. Start Using

    • Switch to BiBi Keyboard in any input field
    • Long press the microphone button to start voice input

๐Ÿ’ก Tip: First-time users are recommended to configure Volcengine for 20 hours of free quota!

๐ŸŽจ Tech Stack

Kotlin 2.3.21
Android SDK (Compile SDK 37, Target SDK 35, Min SDK 26)
Jetpack Compose + Material Design 3 / Miuix
Coroutines (async processing)
OkHttp 5.3.2 (network requests)
SharedPreferences (data storage)
sherpa-onnx (local ASR models)

๐Ÿ“„ License

This project is licensed under the Apache 2.0 License, see the LICENSE file for details.

Apache 2.0 License - Free to use, modify, distribute, must retain copyright notice

Star History

Star History Chart

โ˜• Support & Appreciation

If this project helps you, please give it a Star โญ๏ธ and feel free to buy me a coffee โ˜•๏ธ

WeChat Appreciation Code
Scan with WeChat to appreciate

๐Ÿ™ Acknowledgments

Thanks to the following open-source projects for their technical support:

  • sherpa-onnx - Provides technical support for local ASR models, making offline voice recognition possible
  • TEN-VAD - Provides the current VAD model support
  • SyncClipboard - Provides clipboard synchronization backend service (not running locally, requires server)
  • Phosphor - Provides almost all icons used in the software
  • miuix - Provides Miuix-style Compose UI components, icons, and preference components
  • WaveLineView - Provides beautiful wave animation implementation for audio visualization, making recording experience more fluid and visually appealing
  • Thanks to the author NURKE(ๅ—ใฒบ) of the "Completion Project" icon pack for designing the new application icon for this project

Made with โค๏ธ by BryceWG