Open source real-time translation app for Android that runs locally

Effort to open-source NLLB checkpoints.

A performant high-throughput CPU-based API for Meta's No Language Left Behind (NLLB) using CTranslate2, hosted on Hugging Face Spaces.

This project use the Meta NLLB-200 translation model through the Hugging Face transformers library.

Local-first, open-source YouTube dubbing: clones the original voice into another language, time-synced. Chatterbox voice cloning + faster-whisper + NLLB, with multi-voice, burned subtitles and optional Wav2Lip lip-sync. Runs free on your own machine via a simple CLI.

本地 AI 驱动的实时对话翻译桌面应用（Real time dialogue translation desktop application driven by local AI）

Example application for the task of fine-tuning pretrained machine translation models on highly domain-specific, self-extracted translated sentences

Anchor: A universal, hardware-accelerated CLI tool for subtitle synchronization (Whisper) and context-aware translation (NLLB)

Offline Vietnamese voice AI assistant built on Nemotron-3.5 ASR. 'Nemo ơi' wake word + local skills + Piper TTS. Same pipeline does real-time translation.

Multi-engine neural translator across 200 languages — local NLLB-200 / MADLAD / Ollama + free Gemini/Groq APIs. FastAPI + Next.js.

A desktop tool to automatically transcribe, translate, and embed bilingual subtitles directly into your video files. Uses advanced AI for accurate dual-language generation without exposing private API keys

CLI tool to transcribe (+ translate) videos and embed subtitles automatically.

An offline AI-powered pronunciation trainer for language learners.

Wayland-first local popup translator for Arch Linux and KDE Plasma

AI subtitles for any video — generated, edited and translated 100% in your browser. No uploads, no servers. Static Astro + Whisper/NLLB (transformers.js) + FFmpeg WASM.

AISumNews or shortened for AI Summarized News is an open source application for displaying summarized news content from around the web.

THOTH Language Translator is a powerful, privacy-first, state-of-the art translation tool that runs offline. It uses the NLLB-200 engine to translate over 200 languages, with option to switch to an alternate translation engine, Argos.

Real-time audio translation using Whisper + SeamlessM4T / NLLB-200

Self-hosted speech and text translation service. Whisper (STT) → NLLB-200 (text) → Piper (TTS). .NET 10 · gRPC · ONNX Runtime · Docker.

Multi-modal conversation intelligence system: Real-time transcription, translation, speaker recognition, AR glasses output, and semantic memory capture. Integrates Whisper, NLLB-200, pyannote.audio, Even G2 smart glasses, and Qdrant vector storage.