woheller69/whisperIME

Android Input Method Editor (IME) based on Whisper

What it solves

This project provides an offline, privacy-focused voice recognition system for Android devices. It allows users to convert speech to text without relying on cloud services, serving as either a standalone app, a system-wide voice input service, or an integrated input method editor (IME).

How it works

The app leverages the Whisper engine (via TFLite models) to perform speech-to-text conversion. Upon first launch, it downloads the necessary models from Hugging Face; after this, all processing is done entirely offline. Users can choose between a fast, English-only model or a slower, comprehensive multi-lingual model.

Who it’s for

Android users who want high-quality voice typing and transcription that works offline and protects user privacy.

Highlights

  • Integrated as an Input Method Editor (IME) or a system-wide RecognitionService.
  • Fully offline operation after initial model download.
  • Supports translation of supported languages into English when used as a standalone app.
  • Offers a choice between speed-optimized English models and multi-lingual models.

Related

  • Project
    Notely-Voice/NotelyVoice

    A private, cross-platform AI voice transcription and note-taking app that uses OpenAI Whisper to provide offline speech-to-text capabilities.

  • Project
    niedev/RTranslator

    An offline, real-time translation app for Android that uses on-device AI models like Whisper and NLLB to enable private, internet-free conversations.

  • Project
    OpenWhispr/openwhispr

    OpenWhispr is a cross‑platform desktop app that converts speech to text, provides live meeting transcription with speaker diarisation, and lets you talk to AI assistants (GPT‑5, Claude, Gemini, etc.) directly from your keyboard. It works offline with Whisper‑based models or via cloud services, stores notes locally (with optional cloud sync), and offers an API for programmatic use.

  • Project
    amicalhq/amical

    A local-first, AI-powered dictation and note-taking app that uses Whisper and local LLMs to provide private, context-aware speech-to-text across desktop applications.

  • Project
    ggml-org/whisper.cpp

    A high-performance C/C++ port of OpenAI's Whisper model for efficient, offline, on-device automatic speech recognition across multiple platforms.