Local AI audio transcription and speaker identification app for HR interviews.
Transcribe and diarize sensitive candidate or employee interviews completely on your local machine.
noScribe is a free, open-source desktop application that produces high-quality transcripts of interviews using OpenAI's Whisper and pyannote. It runs entirely on your local machine to protect candidate confidentiality, making it ideal for HR professionals conducting qualitative interviews.
The application automates audio transcription and distinguishes between different speakers while supporting around 60 languages. It features a built-in editor allowing you to review, verify, and correct the generated text directly within the app.
It suits HR professionals and researchers who need strict data confidentiality for sensitive interviews and want to avoid cloud-based third-party processors. It does not suit teams looking for a shared multi-user web service without installing desktop software.
Runs completely on your computer to protect the confidentiality of your interviews.
Distinguishes between different speakers using pyannote integration.
Includes a dedicated editor interface to review, verify, and correct your transcripts.
Can run without its graphical window in a Docker container for server-side batch jobs.
noScribe is free under its open source license, and the only cost is running it yourself on your own hardware.
880 open remote AI-training roles, updated November 15, 2026; most pay $20–$175 an hour. Zekai lists them free; the application goes to the employer’s platform.
No, noScribe runs completely locally on your computer, ensuring total confidentiality for your interviews.
Yes, it integrates pyannote to distinguish between different speakers in the audio file.
See Zekai first in Google