1. Platforms
  2. X (Twitter) Scraper API
  3. X video transcript API

X video transcript API

AI transcription of the video in a post.

GET api.socialscrape.dev/v1/twitter/tweet/transcript

Cost
1 creditAI transcription is billed by the started minute after 2
Cached repeats
0 creditssend max_age_days, results kept 30 days
Failed requests
0 credits

Videos over 2 minutes need allow_long_transcription=true and cost 5 credits per started minute of the whole video. Posts without video, and animated GIFs, answer transcript_unavailable (free).

You send one of url or id.

Part of the X (Twitter) Scraper API: 7 X (Twitter) endpoints on one key.

Request

Send your key in the x-api-key header.

1curl -G "https://api.socialscrape.dev/v1/twitter/tweet/transcript" \2  -H "x-api-key: $SOCIALSCRAPE_API_KEY" \3  --data-urlencode 'url=https://x.com/coinbase/status/2066970874016645585'

Parameters

NameTypeRequiredDescription
urlurlone ofPost URL (x.com/<user>/status/<id>).
idstringone ofPost id. Also accepted as tweet_id.
allow_long_transcriptionbooleanTranscribe audio past 2 minutes with AI, at 5 credits per started minute of the whole video. Without it a longer video answers transcript_unavailable, which is free. Also accepted as allowLongTranscription.

Every request also accepts trim, raw and max_age_days.

Response

Sample from a recorded response, shortened. Values are examples, not your data.

200 OKSample response
1{2  "ok": true,3  "credits_charged": 1,4  "credits_remaining": 4999,5  "cached": false,6  "cached_at": null,7  "request_id": "req_41c6a270e7acc13d323bdbae",8  "data": {9    "object": "transcript",10    "platform": "twitter",11    "video_id": "2111731581702598777",12    "url": "https://x.com/yashsrivasta7a/status/2111731581702598777",13    "language": "en",14    "source": "ai",15    "duration_seconds": 45,16    "text": "Example transcript text. This is illustrative, not the video's real speech.",17    "segments": [18      {19        "start": 0,20        "end": 45,21        "text": "Example transcript text. This is illustrative, not the video's real speech."22      }23    ],24    "available_languages": null,25    "extra": null26  },27  "cursor": null,28  "has_more": null29}

Fields

One Transcript in data.

A field the platform does not give is null, never made up. Extra platform details are in extra.

FieldTypeAlwaysNotes
object"transcript"
platformPlatformyes
video_idstring or null
urlstring or null
languagestring or nullBCP 47, "en"
source"captions" or "auto_captions" or "ai"yes
duration_secondsnumber or null
textstringyes
segmentsTranscriptSegment[] or null
available_languagesstring[] or null
extraobject or null

Full field list in the reference for this endpoint and the data models. Errors are listed under Errors.

Questions

Which errors can it return?

invalid_params (do not retry), unsupported_url (do not retry), not_found (do not retry), transcript_unavailable (do not retry). Account and platform errors from the errors list can also happen. A failure always costs 0 credits.

Is there an SDK call for it?

The Python client has client.twitter.tweet_transcript(...) and the TypeScript client client.twitter.tweetTranscript(). Both return the same envelope as the HTTP API. Install them from PyPI (socialscrape-sdk) or npm (socialscrape); plain HTTP works in any language.

Can an AI agent call it?

Yes. The MCP server, which you run on your own machine, reaches every built endpoint, with the same prices.