API Documentation

Complete reference for GetTranscribe API

Base URL

https://api.gettranscribe.ai

List Transcriptions

Get all your transcriptions with filtering and pagination

GEThttps://api.gettranscribe.ai/transcriptions

Headers

x-api-key: YOUR_API_KEY

Query Parameters

$limitnumber (default: 10) (max: 50)

$skipnumber (default: 0)

folder_idnumber (optional)

platform(Optional) youtube/instagram/tiktok

Example Request

curl -X GET "https://api.gettranscribe.ai/transcriptions?\$limit=20&\$skip=0&\$sort[created_at]=-1" \
  -H "x-api-key: YOUR_API_KEY"

Example Response

{
  "total": 123,
  "limit": 5,
  "skip": 0,
  "data": [
    {
      "id": 4032,
      "user_id": 2,
      "transcription": "A lot of people here are crying that they don't have the money...",
      "platform": "instagram",
      "url": "https://www.instagram.com/p/DM1P8q1MzaG/",
      "thumbnail_url": "https://d.rapidcdn.app/thumb?token=...",
      "download_video_url": "https://d.rapidcdn.app/v2?token=...",
      "duration": "0:30",
      "duration_seconds": 30.159864,
      "word_count": 91,
      "char_count": 515,
      "created_at": "2025-08-07T17:43:15.822Z",
      "updated_at": "2025-08-07T17:43:15.822Z",
      "deleted_at": null,
      "folder_id": null,
      "transcription_analysis": null,
      "original_transcription": "A lot of people here are crying that they don't have the money...",
      "transcription_segments": [
        {
          "id": 0,
          "end": 1.4199999570846558,
          "seek": 0,
          "text": " A lot of people here are crying",
          "start": 0,
          "tokens": [50364, 316, 688, 295, 561, 510, 366, 8554, 50442],
          "avg_logprob": -0.19140006601810455,
          "temperature": 0,
          "no_speech_prob": 0.0340588241815567,
          "compression_ratio": 1.716417908668518
        }
        // ... more segments
      ],
      "transcription_words": [
        {
          "end": 0.20000000298023224,
          "word": "A",
          "start": 0
        },
        {
          "end": 0.30000001192092896,
          "word": "lot",
          "start": 0.20000000298023224
        }
        // ... more words with timestamps
      ],
      "analysis_language": null,
      "download_audio_url": "https://gettranscribe.s3.us-east-1.amazonaws.com/users/2/20250807-124315_6bd26fd0-f3de-4683-8982-5572b6e0079c/compressed_audio.mp3"
    }
    // ... more transcriptions (total of 5 items)
  ]
}

Note: The response includes pagination metadata (total, limit, skip) and an array of transcription objects. Each transcription includes detailed data with word-level timestamps, audio segments, download URLs, and metadata. The transcription_segments and transcription_words arrays have been truncated for brevity.