Transcription API | Unified Agent APIs

Overview

Transcribe audio with speaker diarization and timestamps

Credits

3 credits per call

Providers

Deepgram

SDK Method

client.transcribe(...)

Parameters

audio_urlRequired

string

URL to audio/video file.

language

string (default: en_us)

Language code.

speaker_labels

boolean (default: true)

Enable speaker diarization.

Example Response

{
  "success": true,
  "data": {
    "transcript": "Yeah. As as much as, it's worth celebrating, the first spacewalk with an all female team, I think many of us are looking forward to it just being normal.",
    "confidence": 0.99,
    "language": "en",
    "duration_seconds": 25.93,
    "word_count": 62,
    "speaker_count": 1,
    "utterances": [
      {
        "speaker": 0,
        "text": "Yeah. As as much as, it's worth celebrating,",
        "start": 0.08,
        "end": 3.3,
        "confidence": 0.99
      },
      {
        "speaker": 0,
        "text": "the first, spacewalk,",
        "start": 4.48,
        "end": 5.78,
        "confidence": 0.94
      }
    ]
  },
  "metadata": {
    "provider_used": "deepgram",
    "providers_tried": [
      "deepgram"
    ],
    "mode_used": null,
    "response_time_ms": 1361,
    "request_id": "req_16129e15"
  },
  "credits_used": 3
}

Get Started

Use this API through the O-mega platform. Create an API key in your dashboard, then call the endpoint with your key in the Authorization header.

Try Transcription

Test Transcription in the interactive playground. No setup required.

Open Playground