Supported File Formats

NameQuick processes 30+ file formats across four categories. Each file is analyzed based on its content, not just the filename or extension.

---

How Each Category Is Processed#

Documents#

PDFs, Word documents, and presentations are read for their full text content. NameQuick extracts dates, amounts, vendor names, reference numbers, and document types.

Scanned PDFs are processed with built-in OCR. No separate setup required.

Images#

Images are analyzed visually by the AI provider. NameQuick recognizes scenes, landmarks, objects, brands, and activities. EXIF metadata (camera model, GPS coordinates, timestamps) is used when available.

Audio#

Audio files are transcribed, and names are generated from the spoken content. Supports common formats from voice memos, podcasts, and music recordings.

Video#

Video files are analyzed using keyframes and audio transcription. Supports formats from screen recordings, camera footage, and downloads.

---

Provider Differences#

Not every AI provider supports every format. The colored dots in the table above show which providers handle which categories. Click a dot to see the exact formats supported by that provider.

Managed AI supports all listed formats. If you use BYOK (Bring Your Own Key), check that your chosen provider covers the formats you need.

---

OCR for Scanned Documents#

NameQuick includes built-in OCR for scanned PDFs and images containing text. The OCR runs locally before sending extracted text to the AI provider.

This means scanned invoices, receipts, and handwritten notes work the same as digital documents.

---

EXIF Metadata#

For photos, NameQuick reads EXIF data when present:

• Date taken for chronological naming
• Camera model and lens information
• GPS coordinates for location-based names
• Orientation and resolution data

EXIF data supplements visual analysis. If a photo was taken at the Golden Gate Bridge, NameQuick uses both the GPS location and what it sees in the image.