Latest: JayApp Dark Mode implementation guide is now live!Our AI Code Analysis tool is now in MVP testing.📈 Success Story: E-commerce site achieved 150% traffic growth via JayApp SEO.Tip: Next.js 16 & Tailwind CSS 4 are the gold standard for 2026.Latest: JayApp Dark Mode implementation guide is now live!Our AI Code Analysis tool is now in MVP testing.📈 Success Story: E-commerce site achieved 150% traffic growth via JayApp SEO.Tip: Next.js 16 & Tailwind CSS 4 are the gold standard for 2026.
🎙️

LocalWhisper

Your Voice, Your Device, Your Privacy

AI ProductivityAndroid

Overview

LocalWhisper is an Android app built for users who want powerful AI without sacrificing privacy. In 2026, AI is everywhere — but so is privacy anxiety. Where does your voice data go? Who's listening to your conversations? What are those "free" AI services really doing with your data? LocalWhisper's answer is simple: everything runs locally on your phone. Multi-Engine Speech Transcription Most transcription apps have one engine. LocalWhisper has four: SenseVoice (94%+ Chinese accuracy, auto punctuation, emotion detection), whisper.cpp (99 languages, NEON-optimized), Paraformer (Chinese-optimized, non-autoregressive for blazing speed), and FunASR Nano (Cantonese, Wu Chinese and other dialects). This isn't feature bloat — it's scenario-driven architecture. Use SenseVoice for Chinese meetings, whisper.cpp for English podcasts, Paraformer when speed matters, and FunASR Nano for dialect recognition. Plus, all engines support re-transcription with a different model — something impossible with cloud services. Gemma 4 On-Device LLM Powered by Google's latest open-source Gemma 4 models running locally via LiteRT-LM. Auto-generate summaries and to-do items after transcription. Chat naturally with the AI using voice or text. No internet required — works in airplane mode. Verifiable Privacy Protection Privacy isn't claimed — it's architecturally guaranteed. Audio never leaves your device. No registration required. Zero SDK tracking. Uninstalling removes all data. Internet permission is only used for downloading AI models, never for uploading user data.

Key Features

🎙️

Professional Speech Transcription

Real-time and batch transcription modes with multi-engine architecture covering Chinese, English, Japanese, Korean and more. Auto punctuation, emotion detection, and language identification.

🤖

On-Device AI Assistant

Powered by Gemma 4 on-device LLM with no cloud API and zero privacy risk. Auto-generates summaries and to-do items, supports voice and text conversation.

🔒

Privacy-First Design

All speech recognition and AI inference run entirely on-device. No account registration, no login, no tracking. Uninstalling deletes all data automatically.

⚡

Blazing Fast Experience

whisper.cpp NEON-optimized, SenseVoice single transcription in ~2 seconds. Background transcription with notification progress bar.

🌍

Multilingual Support

UI in Simplified Chinese and English. Transcription supports Chinese, English, Japanese, Korean, plus Cantonese and Wu Chinese dialects.

📁

Smart File Management

Unified file management for recordings and transcripts. Cached AI summaries open instantly. Share via system share sheet and re-transcribe with different models.

Technical Highlights

STT Engine 1SenseVoice (zh/en/ja/ko/yue) — 94%+ Chinese accuracy
STT Engine 2whisper.cpp (multilingual, NEON-optimized)
STT Engine 3Paraformer (Chinese-optimized)
STT Engine 4FunASR Nano (Chinese dialects)
LLM EngineGemma 4 E2B/E4B via LiteRT-LM (on-device)
AccelerationGPU (OpenCL), NPU (NNAPI), CPU (NEON)
Minimum Android9.0+ (API 28)
Architecturearm64-v8a

Permissions

PermissionWhy
Microphone录制语音用于本地转录(完全离线)
Internet仅用于下载 AI 模型,不上传任何数据
Foreground Service在后台运行长转录任务并显示进度通知
Notifications显示转录进度

Ready to experience truly offline AI?

Download LocalWhisper and let AI run on your device, not on someone else's server.