Read on-screen text from TikTok and Instagram posts

Get the text burned into a TikTok video or shown on an Instagram post's images, read by OCR, from the post URL. 50 credits per post.

To read the text shown on a TikTok video, call GET /v1/tiktok/video/screen-text with the video's url: it returns TikTok's native text stickers plus AI OCR of the cover frame, so captions burned in with an editor are caught too. For Instagram, call GET /v1/instagram/media/screen-text with the post's url: it reads the photo, each carousel slide up to 10, or a reel's cover frame, and returns the text per slide. Both cost 50 credits per post.

Cost

50 credits per post on either platform. Reading 100 posts costs 5,000 credits. Asking for the same URL again within 6 hours is answered from the shared cache for 2 credits. Failed calls and empty results are free.

Which text does each endpoint read?

A post carries text in three places, and each has its own endpoint.

Text	TikTok	Instagram
Caption	`GET /v1/tiktok/post` (10 credits)	`GET /v1/instagram/post` (10 credits)
Spoken words	`GET /v1/tiktok/post/transcript` (100 credits)	`GET /v1/instagram/media/transcript` (100 credits)
Text on screen	`GET /v1/tiktok/video/screen-text` (50 credits)	`GET /v1/instagram/media/screen-text` (50 credits)

On TikTok, text typed with TikTok's own text tool is also on GET /v1/tiktok/post as post.ext.on_screen_texts. Use screen-text when you also need text burned into the video by an outside editor, which only OCR can see.

How do I find the URL?

Copy the post's link from the app or browser.

TikTok: a /video/ or /photo/ link, such as https://www.tiktok.com/@stoolpresidente/video/7499229683859426602.
Instagram: a /p/, /reel/, /reels/ or /tv/ link, such as https://www.instagram.com/p/DdEqEl5Dl-S/.

Make the request

cURL

# TikTok video
curl "https://api.insightsocial.app/v1/tiktok/video/screen-text?url=https://www.tiktok.com/@stoolpresidente/video/7499229683859426602" \
  -H "x-api-key: $INSIGHTSOCIAL_API_KEY"

# Instagram post or carousel
curl "https://api.insightsocial.app/v1/instagram/media/screen-text?url=https://www.instagram.com/p/DdEqEl5Dl-S/" \
  -H "x-api-key: $INSIGHTSOCIAL_API_KEY"

What comes back

Real responses from 2026-10-14. The TikTok one is complete:

TikTok response

{
  "success": true,
  "endpoint": "/v1/tiktok/video/screen-text",
  "schema_version": "2",
  "data": {
    "video_id": "7499229683859426602",
    "url": "https://www.tiktok.com/@stoolpresidente/video/7499229683859426602",
    "texts": ["Delicious Pizza"],
    "native_texts": null,
    "ocr_texts": ["Delicious Pizza"],
    "source": "ocr",
    "media_type": "video",
    "frame": "cover"
  },
  "unavailable": [],
  "credits_used": 50
}

Field	What it holds
`data.texts`	All the text found on the video, native and OCR combined.
`data.native_texts`	Text added with TikTok's text tool. `null` here, so everything came from OCR.
`data.ocr_texts`	Text read by AI from the image.
`data.source`	Where the text came from: `ocr` in this response.
`data.frame`	Which frame OCR read: `cover`.

The Instagram one, a 20-slide carousel, shortened: 2 of the 10 slides it read, and image URLs cut.

Instagram response (shortened)

{
  "success": true,
  "endpoint": "/v1/instagram/media/screen-text",
  "schema_version": "2",
  "data": {
    "post_id": "3982493004019425170",
    "shortcode": "DdEqEl5Dl-S",
    "url": "https://www.instagram.com/p/DdEqEl5Dl-S/",
    "media_type": "carousel",
    "texts": [
      "\"Ana, dein Speicherplatz ist voll.",
      "Du musst Fotos löschen\"",
      "...",
      "Ce KLAUSE",
      "Happy\nBirth Day",
      "Notfall: 81",
      "AK: 5122",
      "OA: 5140"
    ],
    "images": [
      {
        "index": 0,
        "image_url": "https://scontent-ord5-1.cdninstagram.com/…",
        "texts": ["\"Ana, dein Speicherplatz ist voll.", "Du musst Fotos löschen\""]
      },
      {
        "index": 2,
        "image_url": "https://scontent-ord5-2.cdninstagram.com/…",
        "texts": []
      }
    ],
    "source": "ocr",
    "frame": null,
    "slide_count": 20
  },
  "unavailable": [],
  "credits_used": 50
}

Field	What it holds
`data.texts`	The text from every slide read, in slide order.
`data.images[]`	One entry per slide read: its `index`, `image_url` and the `texts` on it. A slide with no text has an empty list.
`data.slide_count`	How many slides the post has: 20 here, of which the first 10 were read.
`data.media_type`	The kind of post: `carousel` here.
`data.frame`	`null` for a carousel; for a reel, the frame read is the cover.

What are the limits?

Videos: the cover frame only. On both platforms OCR reads only the cover frame of a video, so burned-in text that appears later in a TikTok or a reel is not read.
Carousels: the first 10 slides. The sample post has 20 slides; images holds 10.
Lines, not sentences. OCR returns text in the lines it sees, so one sentence can arrive as two entries, and an entry can contain a line break ("Happy\nBirth Day"). Join them yourself if you need full sentences.
Not the caption, not the audio. Use the post and transcript endpoints in the table above for those.

What can I build with it?

Hook analysis. Collect the text on the cover frame of top-performing videos in a niche and compare which hooks get the most views.
Carousel research. Pull every slide's headline from a competitor's carousels to see what topics and formats they publish.
Searchable archive. Store caption, transcript and on-screen text together so a search finds a post by any words it shows.

GET /v1/tiktok/video/screen-text reference and GET /v1/instagram/media/screen-text reference: every parameter and field.
GET /v1/tiktok/post/transcript and GET /v1/instagram/media/transcript: the spoken words instead.
Video transcription recipe: transcripts across platforms.
TikTok endpoints and Instagram endpoints.