Offline Voice Input
dev.notune.transcribe
Zapstore _@zapstore.dev Private, offline speech-to-text keyboard powered by AI
Republished from GitHub / F-Droid by the Zapstore main account.
Offline Voice Input delivers professional-grade speech-to-text that runs entirely on your device. Whether you're writing emails, taking notes, or chatting, your voice never leaves your phone — no internet connection, no account, no tracking. VOICE TYPING IN ANY APP Tap the microphone on a compatible keyboard — such as Microsoft SwiftKey — or a website's voice-search button, and Offline Voice Input transcribes your speech straight into the text field. It registers as your device's speech-to-text provider. Note: some keyboards (such as Gboard) only use Google's own voice typing and can't pass speech to other apps. If yours does, switch to a keyboard like SwiftKey — or simply use the built-in voice keyboard described below, which always works. LIVE SUBTITLES Get real-time, on-device captions for any audio or video playing on your phone — videos, podcasts, meetings and more. TRANSCRIBE AUDIO FILES Share an audio file to Offline Voice Input (or open it with the app) to turn the recording into text. OPTIONAL VOICE KEYBOARD Prefer voice input as its own keyboard? A dedicated voice keyboard is included — switch to it whenever you like. WHY YOU'LL LOVE IT • 100% offline — even works in airplane mode, nothing is ever uploaded • Private by design — audio is processed on-device and never stored or sent • Fast and accurate, powered by NVIDIA's Parakeet model • 25 languages, including English, German, French, Spanish, Italian, Portuguese, Dutch, Polish, Russian and Ukrainian • Free and open source (MIT License) The app downloads the speech model (~670 MB) once on first launch; afterwards everything runs locally on your device. POWERED BY OPEN SOURCE We believe in transparency and the power of the community. Offline Voice Input is built with cutting-edge open-source technology: • NVIDIA Parakeet TDT 0.6B — high-performance on-device speech recognition (INT8 ONNX, quantized by istupakov) • transcribe-rs — the Rust transcription engine by CJ Pais • ONNX Runtime — efficient on-device model inference • A native Android interface with a Rust core for speed and safety Source code, issues and contributions: https://github.com/notune/android_transcribe_app
First release: Jul 19, 2026, 1 total release.
Most recent release: Jul 19, 2026.
Appears in 0 app stacks.
0 sats / 0 zaps received in the past year.
Sats Received
Underlying data available via MCP: app_zaps, app_releases.
Zap Count
Underlying data available via MCP: app_zaps, app_releases.
Releases
- Jul 19, 2026 0.1.18v0.1.18 - New engine: switched from transcribe-rs to transcribe.cpp. The built-in Parakeet TDT 0.6B v3 model is now a 485 MB GGUF (down from 670 MB) and the heavy onnxruntime dependency is gone. - Bring your own model: a new speech-models screen lets you import any transcribe.cpp GGUF model fully offline via the file picker, with curated download links, file sizes and delete buttons. - Language & translation: pick a language from a dropdown, plus a translate-to-English option for models that support it (Whisper does, Whisper Turbo mostly doesn't — the status tells you which). - Faster inference: SIMD kernels (dotprod/fp16) and a thread count derived from your CPU's performance cores, with a clear message on very old CPUs instead of a crash. - New thread-count setting and a built-in benchmark, so you can tune threads and see the effect on your own device. - Movable subtitles: the live subtitle overlay can be dragged and remembers where you left it. - Skip the screen-capture prompt: an optional advanced setting lets you grant screen capture once via adb, so live subtitles start without the system dialog every time. - More stable: failed transcriptions no longer freeze the voice keyboard at "Processing", auto-record no longer fires when you tap to move the cursor, and Whisper no longer retries endlessly.
More…
- Now translated into German, French, Spanish, Italian, Portuguese and Russian. - Clearer keyboard help: SwiftKey and AnySoftKeyboard can open the voice panel directly; other open-source keyboards switch to the voice keyboard instead. - UI polish: consistent card icons, correct status-bar colors, and a cleaner models screen.