AI for Transcription in Digital Collections

Join Ninh Tran and Greta Bahnemann as they share their experiences using AI transcription for digital collection items. TranscribeAI is a new tool developed at Minitex that uses Google Gemini to transcribe typed, handwritten, and mixed-text documents. By automatically downloading items from digital repositories (e.g., Minnesota Digital Library) and using metadata to provide context, TranscribeAI produces highly accurate transcripts while reducing staff time and costs. This session will highlight the challenges of traditional OCR and manual transcription, demonstrate how TranscribeAI addresses them, and share best practices for integrating AI-generated transcripts into library workflows. Attendees will learn how AI-driven transcription enhances accessibility, improves discovery through keyword-searchable text, and preserves the cultural integrity of historical documents. We will also discuss lessons learned from recent pilot projects, including the importance of human review and quality assurance. Join us to explore how TranscribeAI can transform your library’s digital collections by increasing discoverability and broadening access for all users.