Skip to main content
Legal-grade transcription with speaker diarization. Add audio transcription to your app—convert recordings, depositions, and calls into verbatim transcripts with speaker identification.

Quick start

import Casedev from 'casedev';

const client = new Casedev({ apiKey: process.env.CASEDEV_API_KEY });

// Submit your user's audio for transcription
const job = await client.voice.transcription.create({
  audio_url: uploadedAudioUrl,
  speaker_labels: true
});

// Poll for results
let result = await client.voice.transcription.retrieve(job.id);
while (result.status !== 'completed') {
  await new Promise(r => setTimeout(r, 5000));
  result = await client.voice.transcription.retrieve(job.id);
}

// Return transcript to your user
console.log(result.text);

Endpoints

Features

Transcription

  • Speaker Diarization — Automatically identify different speakers (e.g., “Speaker 1” vs “Speaker 2”).
  • Court Reporting Formats — Output timecodes and line numbers for legal compliance.
  • Multi-Channel Support — Process multi-track audio for perfect speaker separation.
  • Vocabulary Boosting — Add custom terms (case names, medical terminology) for higher accuracy.

Text-to-Speech

  • Accessibility — Generate audio versions of documents for accessibility compliance.

Pricing

ServiceCost
Transcription$0.30/minute
Text-to-Speech$0.30/1,000 characters
Example: A 2-hour deposition costs $36 to transcribe.