Drop in audio. Get a transcript with speakers.

Request

curl -X POST https://api.whisperly.dev/v1/transcribe \
  -H "Authorization: Bearer $WHISPERLY_KEY" \
  -F "file=@meeting.mp3" \
  -F "diarization=true" \
  -F "word_timestamps=true"

Response

{
  "id": "req_01HX...",
  "status": "succeeded",
  "data": {
    "text": "Hello and welcome to the call.",
    "segments": [
      { "start": 0.0, "end": 2.4, "text": "Hello and welcome.", "speaker": "SPEAKER_00" }
    ],
    "subtitles": {
      "srt": "1\n00:00:00,000 --> 00:00:02,400\n[SPEAKER_00] Hello and welcome.\n",
      "vtt": "WEBVTT\n\n00:00:00.000 --> 00:00:02.400\n<v SPEAKER_00>Hello and welcome.\n"
    },
    "metadata": {
      "duration_seconds": 1842.0,
      "language_detected": "en",
      "speakers_detected": 3,
      "model_used": "small"
    }
  },
  "usage": { "units": 30.7, "unit_type": "minute" }
}