Supported File Formats
Complete list of file formats NameQuick can process, including images, documents, audio, and video.
NameQuick 3 recognizes more than 70 file extensions, from PDFs and Office files to camera RAW, audio and video, on both Mac and Windows. Each file is analyzed based on its content, not just the filename or extension. Whether a recognized file can be analyzed depends on the format and your AI setup, and unknown extensions are not supported.
Recognized file formats#
This is the complete list of extensions NameQuick recognizes, the same on Mac and Windows. The last column describes how Managed, NameQuick's cloud, reads each kind. See the limits below the table for size and length caps.
| Category | Extensions | How Managed reads the content |
|---|---|---|
| Document pages sent to the model; for more than 15 pages, only the first 15. | ||
| Images | JPG, JPEG, PNG, GIF, WebP, BMP, TIF, TIFF, HEIC, HEIF | Sent to the model as an image. |
| Camera RAW | RAW, ARW, CR2, CR3, NEF, DNG, RAF, ORF, RW2, SR2, PEF, RWL, NRW, SRW, 3FR, IIQ, MOS, KDC, MRW, MEF | Through the embedded JPEG preview. Without a usable preview, processing fails. |
| Vector graphics | SVG, AI, EPS | SVG and PDF-compatible Illustrator files are converted to an image. EPS and older Illustrator formats are recognized but can't be processed. |
| Word | DOCX | Extracted text, within a length limit. |
| Excel | XLSX, XLSM | Samples from the sheets. Macros in XLSM files are never run. |
| PowerPoint | PPTX | Extracted text, within a length limit. |
| Apple documents | PAGES, NUMBERS, KEY | The embedded preview image, not the full text. |
| Text, markup and code | TXT, MD, CSV, HTML, CSS, JS, PY, XML, RTF, DOC | Extracted text, within a length limit. |
| Audio | MP3, WAV, M4A, AAC, FLAC, OGG, OPUS, AIF, AIFF, AIFC, CAF, WMA | Sent to the model as media; the result depends on the model. |
| Video | MP4, MPEG, MPG, MOV, AVI, FLV, WEBM, WMV, 3GP | Sent to the model as media; the result depends on the model. |
Listing an extension is not a promise that every model can process every file of that type. Test your own files, especially media and formats that rely on an embedded preview. The table below shows which AI providers handle which categories.
Images
8 formats
Documents
11 formats
Audio
8 formats
Video
9 formats
How Each Category Is Processed#
Documents#
PDFs, Word documents, PowerPoint presentations, spreadsheets, and text files are read for their content so the AI can pick out dates, amounts, vendor names, reference numbers, and document types. Reading has limits: with Managed, a PDF with more than 15 pages is named from its first 15 pages (its receipt in History shows Partial document sent), long Word, PowerPoint, and text files are cut to a length budget, and spreadsheets are sampled rather than read in full. Apple Pages, Numbers, and Keynote files are read from their embedded preview image, not their full text.
Scanned PDFs
Images#
Images are analyzed visually by the AI provider, which can recognize scenes, landmarks, objects, brands, and activities. Camera RAW files are read through their embedded JPEG preview. For how photo metadata is used, see EXIF Metadata.
Audio#
Audio files are sent to the AI model for content analysis where your setup supports audio. Common formats from voice memos, podcasts, and music recordings are accepted. NameQuick does not transcribe audio itself, and it does not fall back to naming from metadata alone: if your setup can't take audio, processing fails with a reason.
Video#
Video files are sent to the AI model for content analysis where your setup supports video. Formats from screen recordings, camera footage, and downloads are accepted. As with audio, there is no metadata-only fallback.
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.
Caution
Managed covers the widest range. With Self-Managed, each connection receives different content:
| Connection | Receives |
|---|---|
| OpenAI, Anthropic, OpenRouter | Text, images, and PDFs. No audio or video. |
| Gemini | The file type directly. |
| Custom OpenAI-compatible server | Images and PDFs. |
| Local: Ollama, LM Studio, MLX | Text, images, and PDFs. No audio or video. |
Check that your chosen setup covers the formats you need.
OCR for scanned documents
For naming, NameQuick has no separate built-in OCR step. The AI model reads the text in scanned PDFs and document photos from the page image. With a local model you need one that reads images, and scanned PDFs are limited to the first three pages.
How well this works depends on the scan. The model can misread characters or words, so check suggested names for blurry or hard-to-read scans before you apply them. Content Search uses on-device OCR for its local index, but that is separate from naming.
EXIF Metadata#
EXIF data such as date taken, camera, and GPS coordinates is read directly by Rules, for conditions and path tokens.
Naming works differently: there is no direct EXIF token for filenames. A Preset field such as "date taken" is filled in by the AI from the image, so the value can be missing or wrong. Don't rely on EXIF or GPS data to decide the suggested name.
Every supported format feeds the same two abilities: Smart Rename names files from this content, and Content Search finds them by it later.