kaixxx/noScribe

Cutting edge AI technology for automated audio transcription. A nice GUI for OpenAIs Whisper and pyannote (speaker identification)

What it solves

noScribe provides a free, open-source tool for creating high-quality audio transcripts of interviews, specifically designed for qualitative social research and journalism. It solves the problem of privacy concerns associated with cloud-based transcription services by running completely locally on the user's computer.

How it works

The application leverages existing AI models for speech-to-text and speaker identification. It integrates OpenAI's Whisper, faster-whisper, and pyannote-audio to handle transcription and distinguish between different speakers across approximately 60 languages.

Who it’s for

It is primarily intended for qualitative researchers, journalists, and anyone needing secure, local audio transcription with speaker identification.

Highlights

  • Local processing for maximum confidentiality
  • Speaker diarization to distinguish between different voices
  • Built-in editor for reviewing and correcting transcripts
  • Cross-platform support for Windows, MacOS, and Linux
  • Support for approximately 60 languages

Related

  • 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
    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
    aTrainTranscription/aTrain

    aTrain is a privacy-focused, offline transcription tool that uses Whisper and pyannote.audio to convert speech recordings into text with speaker detection.

  • Project
    thewh1teagle/vibe

    A private, offline audio and video transcription tool that uses AI models like Whisper to convert speech to text locally on your device.

  • Project
    bugbakery/transcribee

    An open-source audio and video transcription tool that generates automatic drafts using AI and supports collaborative manual editing.