Podcast transcription API with speaker labels

Built for developers who need structured podcast data for AI applications. Get accurate transcripts with automatic speaker diarization and timestamps. Most transcription APIs force you to download → upload files. We accept direct podcast URLs so you can automate everything

Join Waitlist

Know who said what — automatic speaker diarization

Each sentence tagged with speaker IDs and precise timestamps. No manual labeling required.

Clean JSON responses — ready for your AI pipeline

Structured data that works seamlessly with LLMs, RAG systems, and vector databases. No parsing headaches.

Simple REST API — integrate in minutes, not days

Upload audio via URL or file. Get webhooks when processing completes. Standard HTTP, no complex SDKs.

API Example

Request

curl -X POST https://api.unitbytes.com/v1/transcribe \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://example.com/podcast.mp3",
    "speaker_labels": true,
    "webhook_url": "https://yourapp.com/webhook"
  }'

Response

{
  "id": "txn_abc123",
  "status": "processing",
  "estimated_completion": "2025-10-14T10:15:00Z",
  "segments": [
    {
      "speaker": "A",
      "start": 0.0,
      "end": 4.2,
      "text": "Welcome to the show, today we're discussing APIs."
    },
    {
      "speaker": "B",
      "start": 4.5,
      "end": 8.1,
      "text": "Thanks for having me. Developer experience is key."
    }
  ]
}

Pricing

Early access pricing to be announced

Join the waitlist for exclusive launch discount

Get Early Access

Be the first to know when we launch. No spam, just the essentials.