Pathlight Transcript Parser

📄 Drop your PDF transcript here or click to browse

🔧 Parsing Configuration

Entry Delimiter Pattern:

Regex pattern that matches the start of each new transcript entry. Default matches "00 01 22 27 LMP" format.

Exclusion Patterns (one per line):

Text patterns to remove from the transcript. Each line is treated as a separate regex pattern.

Manual Speaker Configuration:

Define the speaker codes and their full names manually.

Test your configuration on a small sample to verify it works before parsing the full document.

Test Results: