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

curl -X POST https://api.case.dev/voice/transcription \
  -H "Authorization: Bearer $CASEDEV_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
casedev voice:transcription create \
  --audio-url "https://storage.example.com/recording.mp3" \
  --speaker-labels
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);
import casedev
import time

client = casedev.Casedev(api_key=os.environ['CASEDEV_API_KEY'])

# Submit your user's audio for transcription
job = client.voice.transcription.create(
    audio_url=uploaded_audio_url,
    speaker_labels=True
)

# Poll for results
result = client.voice.transcription.retrieve(job.id)
while result.status != 'completed':
    time.sleep(5)
    result = client.voice.transcription.retrieve(job.id)

# Return transcript to your user
print(result.text)
job, _ := client.Voice.Transcription.New(ctx, casedev.VoiceTranscriptionNewParams{
	AudioURL:      casedev.F("https://storage.example.com/recording.mp3"),
	SpeakerLabels: casedev.F(true),
})
fmt.Println(job.ID)

Endpoints

Transcription

POST /voice/transcription — Convert audio to text with speaker labels

Text-to-Speech

POST /voice/v1/speak — Generate natural-sounding speech

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$0.01/minute
Text-to-Speech$0.30/1,000 characters
Example: A 2-hour deposition costs $1.20 to transcribe.

Vault

Store transcripts and make them searchable alongside other documents