Twitter Video Transcript - X Video to Text & SRT
Pricing
from $20.00 / 1,000 video transcripts
Twitter Video Transcript - X Video to Text & SRT
Get the transcript of an X (Twitter) video: paste post links, get the spoken words as text plus SRT and VTT subtitles with timestamps, and the post text, author, date, likes and replies. No login. $20 per 1,000 videos (per started 3 min); posts without video and silent videos are free.
Pricing
from $20.00 / 1,000 video transcripts
Rating
0.0
(0)
Developer
Tenfold Fleet
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 days ago
Last modified
Categories
Features
Share
Not affiliated with X Corp. or Twitter. This Actor reads public posts only and never logs in.
What does Twitter Video Transcript do?
Twitter Video Transcript turns the video in an X (Twitter) post into text. Paste post links from x.com or twitter.com and get back the spoken words as a transcript, ready-made SRT and VTT subtitles and timestamped segments, together with the post's own context: its text, author, date, likes and replies.
It works like a small X video to text API: one post in, one clean JSON row out. You can call it from the Apify Console, the Apify API, a schedule, an integration or an AI agent through the Apify MCP server.
Why use it?
- Quote a clip correctly. Journalists and researchers get the exact words said in a viral video, with timestamps to check them against the clip.
- Subtitle a video you are allowed to re-share. The SRT and VTT files drop straight into a video editor or player.
- Feed posts to an LLM. The transcript plus the post text gives an AI agent the whole message, not only the caption.
- Track statements. Run a list of posts from a launch, a debate or a press event every day and keep the transcripts in one dataset.
- Search video content. Index what was said in videos, not only what was typed.
What data can it extract?
| Field | Meaning |
|---|---|
postUrl, postId | The post |
authorHandle, authorName, authorVerified | Who posted it |
postText, createdAt, postLanguage | The post's text, date and language |
likes, replies | Engagement at the time of the run |
views | Only when X reports it for the video, otherwise null |
videoDurationSec, videoUrl, thumbnailUrl | The video |
videoFrom | post, or quoted when the video comes from the quoted post |
language | Detected spoken language |
transcript, wordCount | The spoken words as plain text |
segments | [{ start, end, text }] in seconds |
srt, vtt | Subtitle files as text |
status, error | transcribed, or why a post was skipped for free |
Retweet counts are not part of the output.
How to get the transcript of an X video
- Open the Actor in the Apify Console and click Try for free.
- Paste one or more post links into X (Twitter) post links:
https://x.com/user/status/123..., twitter.com or mobile links,/i/status/links, t.co links or bare post ids. - Leave Spoken language on
auto, or set a two-letter code such asenores. - Pick the output formats you need (text, SRT, VTT, segments).
- Click Start and download the results.
How much does it cost?
You pay per transcribed video: $20 per 1,000 videos ($0.02 each). A video longer than 3 minutes counts once per started 3 minutes, so a 10-minute clip costs $0.08. There is no monthly fee.
These rows are free: posts without a video, animated GIFs, deleted posts, protected or restricted posts, videos with no sound or no speech, videos over your length limit, and any download or speech-to-text failure.
Free Apify plan: up to 10 posts per run and videos up to 3 minutes. Any paid Apify plan removes both limits (the length limit is then your maxVideoMinutes, up to 180).
Input
Output
Download the dataset as JSON, CSV, Excel, XML or HTML, or read it through the Apify API.
Tips
- One post, one row. Each link gives one result, in any order you paste them. Duplicate links are processed once.
- Quoted videos. A post that quotes a video post gets the quoted video's transcript; turn
includeQuotedVideooff to skip those. - Long videos are split into 10-minute parts and joined back, with timestamps across the whole video.
- Language hint. Short or noisy clips come out better with the language set.
- Proxy. Datacenter proxies are used by default. When X rate-limits them, that post is retried on a residential IP automatically.
FAQ
Can it monitor an account or a timeline?
No. Account, timeline, search and hashtag monitoring are not supported: X blocks those lookups for logged-out visitors. Give the Actor links to single posts. Profile links come back as free rows that say so.
Does it need my X login or cookies?
No. It uses only what X shows to logged-out visitors.
What about posts with several videos?
The first video of the post is transcribed.
What languages does it support?
Around 100 spoken languages, detected automatically.
Why is my post marked no_speech?
The video has music or ambient sound but no speech. Those rows are free.
Can I use it from an AI agent?
Yes. Add it as a tool through the Apify MCP server, or call the Apify API with the post links.
Disclaimer
This Actor processes publicly available posts. You are responsible for how you use the transcripts, including copyright and privacy rules in your country. Transcripts are made by automatic speech recognition and can contain mistakes.
