Twitter Video Transcript API – AI Video to Text for X (Twitter) avatar

Twitter Video Transcript API – AI Video to Text for X (Twitter)

Pricing

from $1.00 / 1,000 results

Go to Apify Store
Twitter Video Transcript API – AI Video to Text for X (Twitter)

Twitter Video Transcript API – AI Video to Text for X (Twitter)

Twitter Video Transcript API for converting video audio into accurate text using AI. Extract transcripts, spoken content, and metadata from X (Twitter) videos, tweets, and threads. Fast, reliable, and built for developers, AI agents, and automation workflows.

Pricing

from $1.00 / 1,000 results

Rating

0.0

(0)

Developer

APISmith

APISmith

Maintained by Community

Actor stats

0

Bookmarked

6

Total users

3

Monthly active users

5 days ago

Last modified

Share

🎙️ Twitter Transcripts Scraper API

Turn Twitter videos into clean, structured transcripts with ease.
This API helps you extract spoken content (auto-generated transcripts) from public Twitter videos — designed for developers, data teams, and AI agents that need text, not just media.


📌 Overview

The Twitter Transcripts Scraper API allows you to provide an Twitter video URL and receive:

  • 📝 Accurate auto-generated transcript text
  • ⏱️ Timestamped segments for precise alignment
  • 📊 Rich video & author metadata
  • 🎥 Direct video and audio URLs (when available)

It is built to be AI-ready, automation-friendly, and cost-effective, making it ideal for large-scale content processing and language-focused workflows.

⚠️ This API works with public Twitter videos. A valid sessionid may be required for stable access.


🎁 What You Can Get From This API

For each Twitter video URL, the API returns:

  • Full transcript text (auto speech-to-text)
  • Segmented transcript with timestamps
  • ✅ Video title & thumbnail
  • ✅ Video, audio playback URLs
  • ✅ Engagement metrics (likes, comments)
  • ✅ Creator profile information
  • ✅ Error status per request (safe for automation)

All data is returned in structured JSON, ready to feed directly into databases, AI pipelines, or downstream services.


🧩 Typical Use Cases

💡 This API is especially useful for:

  • 🤖 AI agents & LLM pipelines (speech → text ingestion)
  • 🧠 Content understanding & summarization
  • 🔍 Social media content analysis
  • 🎧 Audio-to-text & subtitle generation
  • 📊 Trend and language research
  • 🔁 Batch transcription of Twitter videos

If your workflow depends on what is being said, not just what is being shown — this API is built for you.


💰 Cost of Usage

Simple, transparent, and extremely cost-effective.

  • 💵 $1.00 / 1,000 results
  • 🎙️ Audio-to-text (auto transcript) included
  • 📦 Pay only for what you process — no subscriptions

Perfect for both experiments and large-scale AI workloads.


📥 Input Parameters

(1) Input Format

FieldTypeRequiredDescription
videoUrlstringYesPublic Twitter video URL

(2) Input Example

{
"videoUrl": "https://x.com/Dell_JPN/status/1975063471155970378"
}

📤 Output Parameters

(1) Output Format Description

FieldTypeDescription
urlstringNormalized Twitter video URL
codestringTwitter shortcode
pkstringTwitter internal post ID
idstringCombined media identifier
titlestringVideo title or hashtag
imgstringVideo thumbnail URL
videoUrlstringDirect video playback URL
audioUrlstringDirect audio playback URL
createTimenumberVideo creation timestamp
likeCountnumberNumber of likes
commentCountnumberNumber of comments
userPkstringCreator user ID
userNamestringCreator username
userFullNamestringCreator display name
avatarUristringCreator avatar image URL
textstringFull transcript text
segmentsarrayTranscript segments with timestamps
errMsgstringError message (empty if success)
timestampstringAPI response timestamp (ISO format)

(2) Output Example

{
"url": "https://www.instagram.com/p/DTxiM0Ijqvz/",
"code": "DTxiM0Ijqvz",
"pk": "3814980773552761843",
"id": "3814980773552761843_48143082417",
"title": "#explore",
"img": "https://scontent-iad3-1.cdninstagram.com/v/t51.71878-15/619803343_1676825200367728_8092852255612155538_n.jpg?stp=dst-jpg_e15_tt6&_nc_cat=1&ig_cache_key=MzgxNDk4MDc3MzU1Mjc2MTg0Mw%3D%3D.3-ccb7-5&ccb=7-5&_nc_sid=58cdad&efg=eyJ2ZW5jb2RlX3RhZyI6InhwaWRzLjY0MHgxMTM2LnNkci5DMiJ9&_nc_ohc=rQ0gvouEDUUQ7kNvwFFUA3e&_nc_oc=AdklJA8qtEC78q8uoqfq0hrHEHG_Anx14Y98_0qd-0RJTarw5mUGWP-0URYuPxKpVBw&_nc_ad=z-m&_nc_cid=0&_nc_zt=23&_nc_ht=scontent-iad3-1.cdninstagram.com&_nc_gid=1dbJ6M6MmLLlo-Jn7XlUIw&oh=00_AftPbGx5Lc3HrTwQ9YZEkCXoEVvn8Zm9VfQacfUkm8Xw1A&oe=6988A7DB",
"videoUrl": "https://scontent-iad3-1.cdninstagram.com/o1/v/t2/f2/m367/AQMMUMfbkOPXkBEc4m-czR-nbdlRK3No6f05Grxopvsdq-Qg_r6pzR3qzX4VCBojSH6jpNyKgWkW-6fqtrwkdzNgO8NuKmPs4rrnfKQ.mp4?_nc_cat=104&_nc_sid=9ca052&_nc_ht=scontent-iad3-1.cdninstagram.com&_nc_ohc=b76plwG5k3UQ7kNvwESHCkA&efg=eyJ2ZW5jb2RlX3RhZyI6ImlnLXhwdmRzLmNsaXBzLmMyLUMyLmRhc2hfcjJldmV2cDktcjFnZW4ydnA5X3E4MCIsInZpZGVvX2lkIjpudWxsLCJvaWxfdXJsZ2VuX2FwcF9pZCI6OTM2NjE5NzQzMzkyNDU5LCJjbGllbnRfbmFtZSI6ImlnIiwieHB2X2Fzc2V0X2lkIjoxNzcxNTY1Njg3MTU0MjE1LCJhc3NldF9hZ2VfZGF5cyI6MTMsInZpX3VzZWNhc2VfaWQiOjEwODI3LCJkdXJhdGlvbl9zIjoxNCwiYml0cmF0ZSI6NTQwNTE1MywidXJsZ2VuX3NvdXJjZSI6Ind3dyJ9&ccb=17-1&_nc_gid=1dbJ6M6MmLLlo-Jn7XlUIw&_nc_zt=28&oh=00_Afv44NEfcLEiqZgYI0xps4ZZ93tPRuPgqh8oXzgl3VoNxg&oe=6988B5C9",
"audioUrl": "https://scontent-iad3-1.cdninstagram.com/o1/v/t2/f2/m78/AQNngK6i_-6sgwETrVf-d2vgpHQhPoijZmLHAuSp3jU1SijGlVId7zmIXIaJ6pNVuNgpmNGRkHQdLsjdGUauEBi9U1BjR-esFvBHdfw.mp4?_nc_cat=104&_nc_sid=9ca052&_nc_ht=scontent-iad3-1.cdninstagram.com&_nc_ohc=ECX7BSThaXkQ7kNvwH-UVWe&efg=eyJ2ZW5jb2RlX3RhZyI6ImlnLXhwdmRzLmNsaXBzLmMyLUMyLmRhc2hfbG5faGVhYWNfdmJyM19hdWRpbyIsInZpZGVvX2lkIjpudWxsLCJvaWxfdXJsZ2VuX2FwcF9pZCI6OTM2NjE5NzQzMzkyNDU5LCJjbGllbnRfbmFtZSI6ImlnIiwieHB2X2Fzc2V0X2lkIjoxNzcxNTY1Njg3MTU0MjE1LCJhc3NldF9hZ2VfZGF5cyI6MTMsInZpX3VzZWNhc2VfaWQiOjEwODI3LCJkdXJhdGlvbl9zIjoxNCwiYml0cmF0ZSI6ODQxODcsInVybGdlbl9zb3VyY2UiOiJ3d3cifQ%3D%3D&ccb=17-1&_nc_gid=1dbJ6M6MmLLlo-Jn7XlUIw&_nc_zt=28&oh=00_AfvPFX3-VjMr5JtDwrX7wQkOILLeANNhb4zBuw9SU0DR3w&oe=6984DC3D",
"createTime": 1769001195,
"likeCount": 171650,
"commentCount": 781,
"userPk": "48143082417",
"userName": "theavamariee",
"userFullName": "Ava Marie",
"avatarUri": "https://scontent-iad3-1.cdninstagram.com/v/t51.2885-19/572902973_18067009538602418_5617968281035790488_n.jpg?stp=dst-jpg_s150x150_tt6&efg=eyJ2ZW5jb2RlX3RhZyI6InByb2ZpbGVfcGljLmRqYW5nby4xMDgwLmMyIn0&_nc_ht=scontent-iad3-1.cdninstagram.com&_nc_cat=1&_nc_oc=Q6cZ2QHrB35R1hAV3-uIB5VTub-6RuiKV9psrvKni0oh6LvCvBnLGT24jt8xn1dfOPE5zM0&_nc_ohc=X48rTGGGJl8Q7kNvwFwYnWY&_nc_gid=1dbJ6M6MmLLlo-Jn7XlUIw&edm=APs17CUBAAAA&ccb=7-5&oh=00_AfvSE_cEd3Z5ja79s40JOWwAE3JIGmyySyCKLkoRBpTeJg&oe=6988A991&_nc_sid=10d13b",
"text": "Excuse me, miss. What? Your shirt's backwards.",
"segments": [
{
"start": 0.3,
"end": 1.16,
"text": " Excuse me, miss."
},
{
"start": 1.32,
"end": 1.62,
"text": " What?"
},
{
"start": 2.04,
"end": 2.96,
"text": " Your shirt's backwards."
}
],
"errMsg": "",
"timestamp": "2026-02-04T06:38:58.379Z"
}

⭐ Why This API Is Different

🚀 Focused on transcripts, not noise

  • 🧠 AI-first design
    Clean transcripts + timestamps, perfect for LLMs and agents.

  • 🎯 Transcript over transformation
    No summaries, no rewrites — just reliable raw text.

  • 💸 Extremely cost-efficient
    One of the lowest-cost Twitter transcript solutions available.

  • 📦 Automation-safe
    Stable fields, predictable structure, batch-friendly responses.

  • 🌍 Built for real-world usage
    Designed by a team experienced in large-scale social content extraction.


📝 Notes

  • Only public Twitter videos are supported
  • A valid sessionid improves stability and success rate
  • Transcript accuracy depends on audio clarity and language
  • Please ensure compliance with Twitter terms and local regulations
  • Free users can only try video transcription with a duration of no more than 5 minutes, while paid users are not limited by the duration.

🆘 Support

Questions, feedback, or feature requests?

📧 Email: support@apismith.online