API Overview

import {
  estimateSegmentFromToken,
  markAndCombineSegments,
  formatSegmentsToTimestampedTranscript,
} from 'paragrafs';

// Create a segment from a multi-word token
const token = {
  start: 0,
  end: 5,
  text: 'Hello world from paragrafs'
};
const segment = estimateSegmentFromToken(token);

// Process and format segments
const segments = [segment];
const processed = markAndCombineSegments(segments, {
  fillers: ['uh', 'umm'],
  gapThreshold: 3,
  maxSecondsPerSegment: 12,
  minWordsPerSegment: 3,
});

// Generate timestamped transcript
const transcript = formatSegmentsToTimestampedTranscript(processed, 10);
console.log(transcript);
// Output: "0:00: Hello world from paragrafs"

type Token = {
  start: number;  // Start time in seconds
  end: number;    // End time in seconds
  text: string;   // The transcribed text
};

type Segment = Token & {
  tokens: Token[];  // Word-by-word breakdown
};