mkiol/dsnote

Speech Note Linux app. Note taking, reading and translating with offline Speech to Text, Text to Speech and Machine translation.

What it solves

Speech Note is a privacy-focused note-taking application that allows users to create, read, and translate notes across multiple languages without requiring an internet connection. It eliminates the need to send personal data to cloud services by processing all voice and text locally on the user's device.

How it works

The application integrates several open-source processing engines to handle different AI tasks:

  • Speech to Text (STT): Uses engines like Whisper.cpp, Faster Whisper, Vosk, and Coqui STT to convert spoken words into text.
  • Text to Speech (TTS): Employs a wide variety of engines including Piper, Kokoro, F5-TTS, and Parler-TTS to read text aloud.
  • Machine Translation (MT): Utilizes the Bergamot Translator for offline translation between languages.

Users can download the specific language models (checkpoint files) they need through a built-in graphical model browser within the app.

Who it’s for

It is designed for Linux desktop and Sailfish OS users who need a multilingual note-taking tool that prioritizes data privacy and offline functionality.

Highlights

  • Fully Offline: All processing happens locally, ensuring no data is sent to the internet.
  • Multilingual Support: Extensive language coverage for STT, TTS, and translation.
  • Engine Diversity: Supports a vast array of specialized AI engines for speech and translation.
  • Integrated Model Management: Built-in browser for easy downloading of required 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
    homelab-00/TranscriptionSuite

    A free, open-source transcription app that converts speech to text locally on your computer using various AI models for privacy and speed.

  • Project
    goodroot/hyprwhspr

    A native Linux speech-to-text tool providing fast, private, and system-wide dictation using local or cloud-based AI models.

  • Project
    soniqo/speech-swift

    Speech Swift is an open‑source Swift package that provides dozens of on‑device speech AI models (ASR, TTS, translation, voice agents, enhancement, etc.) for Apple Silicon. It runs via Core ML and the MLX framework, supports hundreds of languages, offers multiple quantised sizes, and can be added to a project with a single Swift‑Package‑Manager dependency. The repo includes extensive docs, pre‑trained models, and example code for transcription, streaming dictation, and UI components, all without any cloud calls.

  • 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.