RTranslator 2.1.5 is an Android app for people who want to translate spoken conversations without sending speech to a cloud service. It runs speech recognition and translation on the phone and works offline after an initial model download of about 1.2 GB. The app's code is open source under Apache 2.0, though it uses some closed-source components and its NLLB translation model has a non-commercial restriction.
Conversation mode connects phones over Bluetooth and translates speech in both directions. Each participant hears the translation through their phone's speaker or a Bluetooth headset. It supports conversations with multiple participants, so it isn't limited to a pair of phones.
For brief exchanges with someone who doesn't have the app, WalkieTalkie mode lets two people share one phone and take turns speaking. It recognizes which of the two selected languages a person speaks, translates their words, and reads the result aloud. This mode doesn't support Bluetooth headsets. There's also a text translator with copy and spoken playback controls.
Whisper handles speech recognition, while NLLB handles translation through ONNX Runtime. The app needs at least 6 GB of RAM and a sufficiently fast phone CPU for practical response times. Spoken output uses Android's system text-to-speech engine, which determines voice quality and available spoken languages. Use a TTS engine and voice packs that work offline for offline spoken playback.
The developer says the app doesn't collect personal data. In connected conversations, phones exchange transcribed text rather than sending it to a central server. Both voice modes can keep working in the background or with the phone on standby, though some phones restrict background processing.
The separate 3.0 beta changes translation models. Its Bergamot, Madlad and HY-MT options belong to that prerelease.
Claim this page and we'll verify you by hand. RTranslator gets the verified badge, and you can upgrade the listing to be featured on localhosted. Proud to be listed? Put our badge on your site.
Want more people to find RTranslator?Promote it
Something wrong or outdated on this page?
293Updated 1 day agoApache-2.0
Android#Multilingual#Ollama integration#OpenAI-compatible API
Dictate Keyboard is an Android keyboard for people who prefer speaking to typing or find typing uncomfortable. It runs on Android 8.0 and later, with offline speech recognition on the phone and optional cloud or self-hosted providers. The app is open source under Apache 2.0 and builds on FlorisBoard.
24.8KUpdated 21 hours agoApache-2.0
iOS · Android#Agent Skills#Hugging Face integration#Multilingual
643Updated 1 month agoMIT
Android#Hugging Face integration#Multilingual#Voice activity detection
1.4KUpdated 16 hours agoAGPL-3.0
macOS · Windows · Linux · Browser Extension#Multilingual#ONNX#OpenAI-compatible API
sindresorhus.comOn-Device and In-Browser AI
macOS · iOS#Batch processing#Multilingual
247Updated 3 days ago
Android#GGUF#Hugging Face integration#llama.cpp backend
OfflineLLM is an on-device AI chat app for Android users who want conversations to stay on their phone. It runs entirely offline and has no network permissions, so the app can't send prompts or responses to a cloud service. It requires Android 13 or later on a 64-bit ARM device.
Google AI Edge Gallery is an open-source app for people who want to try generative AI on their own phone. It runs model inference locally, so offline chat, image analysis and audio tasks don't send your inputs to a server. It supports Android and iOS and uses the Apache 2.0 license.
WhisperIME turns speech into text on your Android device using OpenAI Whisper. It's for people who want private dictation in their keyboard or a separate app for transcription and translation. Speech recognition runs entirely offline after an initial model download from Hugging Face, so audio stays on your device during recognition.
Sokuji is a free, open source speech translator for people joining meetings across languages. It sends your translated speech through a virtual microphone, so other participants hear ordinary call audio and don't need to install anything. Their replies appear as translated subtitles on your screen.
Aiko is a paid, native transcription app for macOS, iOS and visionOS that processes speech on your device with OpenAI's Whisper model. It's for people turning meetings, lectures or other recordings into text while keeping the audio local, including sensitive recordings.