API Docs

Create Transcription

Create a new transcription from an Instagram, TikTok, YouTube, Google Drive, Pinterest, Facebook, X, or direct video URL

POSThttps://api.gettranscribe.ai/transcriptions

Headers

Content-Type: application/json

x-api-key: YOUR_API_KEY

Body Parameters

urlrequired

string

The video URL to transcribe (Instagram, TikTok, YouTube, etc.)

folder_idoptional

number

ID of the folder to organize the transcription

languageoptional

string

ISO-639-1 language code (e.g., "en", "es", "fr") to improve transcription accuracy

modeloptional

string

Optional transcription profile. Supported values: "fast", "quality", "speakers", "legacy". Defaults to "fast" when omitted.

promptoptional

string

Context text to guide transcription (names, technical terms, domain-specific vocabulary). Ignored when model is "speakers".

Example Request

curl -X POST https://api.gettranscribe.ai/transcriptions \
  -H "Content-Type: application/json" \
  -H "x-api-key: YOUR_API_KEY" \
  -d '{
    "url": "https://www.instagram.com/p/DWy1RmFAGjF/",
    "folder_id": 123,
    "model": "fast",
    "language": "en",
    "prompt": "This video contains entrepreneurship and motivational content"
  }'

Example Response

{
  "id": 166263,
  "user_id": 1,
  "transcription": "First paragraph of the transcript text.\nSecond paragraph continues here...",
  "platform": "instagram",
  "url": "https://www.instagram.com/p/DWy1RmFAGjF/",
  "thumbnail_url": "https://gettranscribe.s3.us-east-1.amazonaws.com/users/1/20260411-143840_31d7369a-6684-4fee-8a9d-9a1e6fe7a2b6/thumbnail.jpg?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=...&X-Amz-Date=...&X-Amz-Expires=...&X-Amz-Signature=...",
  "download_video_url": "https://www.instagram.com/p/DWy1RmFAGjF/",
  "download_audio_url": "https://gettranscribe.s3.us-east-1.amazonaws.com/users/1/20260411-143840_31d7369a-6684-4fee-8a9d-9a1e6fe7a2b6/compressed_audio.mp3?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=...&X-Amz-Date=...&X-Amz-Expires=...&X-Amz-Signature=...",
  "duration": null,
  "duration_seconds": 100.066,
  "word_count": 251,
  "char_count": 1835,
  "created_at": "2026-04-11T14:38:40.310Z",
  "updated_at": "2026-04-11T14:38:40.310Z",
  "deleted_at": null,
  "folder_id": null,
  "transcription_analysis": null,
  "openai_transcription_analysis_cost": null,
  "openai_transcription_analysis_model": null,
  "s3_video_path": null,
  "s3_audio_path": "users/1/20260411-143840_31d7369a-6684-4fee-8a9d-9a1e6fe7a2b6/compressed_audio.mp3",
  "s3_thumbnail_path": "users/1/20260411-143840_31d7369a-6684-4fee-8a9d-9a1e6fe7a2b6/thumbnail.jpg",
  "original_transcription": "Same text as transcription without the extra newline formatting...",
  "transcription_segments": [],
  "transcription_words": [],
  "analysis_language": null,
  "language": null,
  "prompt": "Transcribe this audio completely word by word with full accuracy...",
  "user_ip": null,
  "user_country": null,
  "user_country_code": null,
  "user_region": null,
  "user_city": null,
  "user_timezone": null,
  "user_latitude": null,
  "user_longitude": null,
  "user_org": null,
  "source": "api",
  "author": "Daniel Vengoechea",
  "author_id": "1492796409",
  "channel": "emegrowthagency",
  "like_count": -1,
  "comment_count": null,
  "view_count": null,
  "video_description": "Caption or description from the post when available...",
  "video_width": 1080,
  "video_height": 1920,
  "upload_timestamp": "1775487293",
  "upload_date": "20260406",
  "video_title": "Video by emegrowthagency",
  "generated_title": "Marketing Médico Moderno: Estrategias para Aparecer y Convertir Pacientes",
  "consumption_type": "purchased",
  "download_method": "yt-dlp-proxycheap-dash-audio",
  "proxy_used": true,
  "proxy_provider": "proxycheap"
}

Example shaped from a live POST (April 2026) for the Instagram URL in the sample curl. download_audio_url and thumbnail_url are short-lived presigned HTTPS URLs on Amazon S3 when files are stored for your account. download_video_url is often the original post or page URL, not a direct MP4 link—do not treat it as a hotlinkable media file unless it clearly points to a CDN or file host. duration may be null while duration_seconds is set. transcription_segments and transcription_words are often empty arrays depending on pipeline and model. The API may also include raw_metadata as a large JSON string from the extractor. Omit optional request body fields you do not need.