aTrainTranscription/aTrain

Health v2 · maintenance only

Adoption not part of the score

1205 stars · 91 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

aTrain is a desktop GUI application for offline transcription of speech recordings using Whisper-based machine learning models, with speaker diarization via pyannote.audio. It runs entirely locally to preserve privacy and support GDPR compliance, and is distributed via Flathub and the Microsoft Store.

Use cases

• transcribe interview recordings offline
• transcribe audio without uploading to the cloud
• add speaker labels to a transcript automatically
• transcribe research interviews in a GDPR-compliant way
• convert meeting recordings to text locally
• transcribe audio in multiple languages on my laptop
• offline speech-to-text for sensitive recordings

When to choose

• you need transcription of sensitive audio that must never leave your device
• you want a simple GUI instead of scripting Whisper yourself
• you need speaker diarization alongside transcription
• you work with many languages and want local processing

When to avoid

• you need real-time streaming transcription
• you want a cloud API with high-throughput batch processing
• you need a CLI-only or headless server workflow
• your hardware cannot run local ML models efficiently

Facets

application · maturity active

speech-recognition gui machine-learning nlp speech-processing privacy desktop-applications developer-tools windows cross-platform python transcription whisper speaker-diarization offline gdpr faster-whisper pyannote natural-language-processing linux desktop

Member repositories

For agents

markdown · JSON · MCP: product_card(name="aTrainTranscription/aTrain")