Supported File Types

Supported extensions are listed below. A supported extension does not guarantee that a damaged, encrypted, or unreadable file can be analyzed. RenameClick preserves extensions and does not convert the original files.

Images

EXIF Metadata

Photos (especially JPEG and HEIC from cameras/phones) often contain EXIF metadata:

• Capture date and time
• Camera make and model
• GPS coordinates (location)
• Lens information
• ISO, aperture, shutter speed

This metadata can be used in format patterns with $exif{} placeholders. See Format Patterns & EXIF.

Documents

How Documents Are Processed

1. Text is extracted from the document using format-specific methods
2. Extracted text is truncated to the text trim limit (default: 4,500 characters)
3. Truncation strategy:
   • Head only: First N characters (default for most documents)
   • Head + Tail: First N/2 + Last N/2 characters (includes the beginning and end, omitting the middle)
4. Data-heavy files (lots of numbers) use smaller limits to avoid token overflow
5. With custom instructions, lines that mention the requested fields and dates are kept when a long document is trimmed
6. The truncated text is sent to the AI for analysis

Scanned PDFs and Photographed Documents

If a PDF contains no extractable text (it's a scanned image):

1. The first page is rendered as an image
2. The text recognition built into macOS or Windows reads that page on your device; the recognized text and a small copy of the page go to the AI together
3. If no readable text is found, the page image alone is analyzed visually. Later scanned pages are not included, and this does not validate signatures or accounting fields.

Photographed documents such as invoices, receipts, and tickets are read the same way. Ordinary photos and small screenshots are analyzed as images. The recognized text for each file is shown by the What the AI saw action in the results.

Mixed PDFs

When some pages contain text and others are scans, the extracted text is sent together with an image of the first scanned page in one request.

Audio

Install Audio Transcription in AI & Models before processing audio. RenameClick transcribes speech on your device and uses the transcript context to suggest a smart filename. With RenameClick Local AI selected, both transcription and filename generation stay on-device.

Short recordings are analyzed in full. Longer recordings are sampled across their duration using the Analyze up to limit configured in AI & Models. The default is 5 minutes. Available limits are 30 seconds, 1 minute, 2 minutes, 5 minutes, and 10 minutes. Sampling may miss a brief important passage.

Audio smart naming is designed for recordings with intelligible speech. It is not a music-identification or acoustic-fingerprinting service. Embedded audio tags and technical metadata are also available through explicit $audio{...} format placeholders.

Unsupported Files

Files with unsupported extensions are skipped during drag & drop and folder scanning, and not counted toward batch limits.

Common unsupported formats include video files (.mp4, .mov, .mkv, .webm), other audio formats (.ogg, .opus, .aiff, .caf, .wma), older Office formats (.xls, .ppt), email (.eml, .msg), archives (.zip, .rar, .7z), and executables (.exe, .app).