noScribe
Local AI transcription app turns interviews into multilingual transcripts on Windows, macOS and Linux, with speaker identification and an editor.
Alternative to:
noScribe transcribes recorded interviews for qualitative researchers and journalists who need to keep audio on their own computer. It processes recordings locally rather than sending them to a cloud transcription service.
- Interview transcription: Whisper speech recognition, through faster-whisper, produces transcripts of interviews in multiple languages.
- Speaker identification: pyannote distinguishes speakers so you can follow who said what in a conversation.
- Transcript review: The built-in editor lets you check the generated text and correct it before using it for analysis or quotations.
noScribe is free and open source under GPL-3.0. It runs on Windows, macOS and Linux, and audio processing stays on the computer running the app.