Video Transcriber - Any Link to Text, SRT & VTT (7 Platforms)
Pricing
from $20.00 / 1,000 video transcribeds
Video Transcriber - Any Link to Text, SRT & VTT (7 Platforms)
Transcribe a video from any link to text: TikTok, Instagram, Facebook, X, YouTube, Vimeo, MP4/MP3/M3U8 files, Google Drive and Dropbox. Get text, SRT and VTT subtitles with timestamps, plus an optional AI summary. $20 per 1,000 videos up to 10 min; failed links are free.
Pricing
from $20.00 / 1,000 video transcribeds
Rating
0.0
(0)
Developer
Tenfold Fleet
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
3 days ago
Last modified
Features
Share
What does Video Transcriber do?
Video Transcriber turns a link to almost any public video into text. Paste links from TikTok, Instagram, Facebook, X (Twitter), YouTube and Vimeo, direct MP4, MOV, WebM, MP3 or M3U8 files, or Google Drive and Dropbox share links, mixed in one list. Each link comes back as one row with the full transcript, SRT subtitles, WebVTT subtitles, timestamped JSON segments, the detected language, the title, author and length, and on request an AI summary with key points.
Not affiliated with TikTok, Instagram, Meta, X, YouTube, Vimeo, Google or Dropbox. All names are trademarks of their owners.
It works like a video to text API you don't have to host. When a platform already has captions for the video (TikTok, Vimeo, YouTube) they are used, which is fast and exact. Otherwise the Actor downloads the audio, converts it with ffmpeg and runs Whisper speech recognition in about 100 languages. YouTube is captions only: a YouTube video without captions is a free error row.
Bulk work on one platform? This Actor is built for mixed, single video links. For whole profiles, feeds, channels or shows, our per-platform Actors are the better choice: TikTok Transcripts, Instagram Reels Transcript, YouTube Transcript Scraper, Podcast Transcription and Audio Transcription (long recordings and files).
Why transcribe videos?
- 📝 Content repurposing: turn a talk, reel or clip into a blog post, thread or newsletter draft.
- 🎬 Subtitles: SRT and VTT files are ready for editors, players and re-uploads.
- 🔎 Research and monitoring: read what creators, brands or officials said in a video without watching it.
- 🤖 AI agents and RAG: timestamped segments are easy to chunk, embed and cite back to the second; the optional summary gives a quick first read.
- ⚙️ Automation: call it from your code, Make, Zapier or n8n and get JSON back.
What data does it return?
| Field | Example |
|---|---|
text | the whole transcript as one string |
srt, vtt | the transcript as SRT and WebVTT subtitle files |
segments | [{ "start": 4.46, "end": 9.26, "text": "..." }], times in seconds |
summary, keyPoints | 3-5 sentences and up to 5 points (only with "Add an AI summary") |
platform, url, videoId | X, the canonical video URL, its id |
title, author, durationSec | post text or video title, creator, length |
transcriptSource, captionType | captions (creator / auto / translated) or speech-to-text |
language, wordCount | en, 266 |
transcribedSec, truncated, chargedExtraMinutes | speech-to-text length, whether it was cut, extra minutes billed |
notice, error | why a video was cut, or why it failed (error rows are free) |
How to transcribe a video from a link
- Open the Actor and click Try for free.
- Paste one video link per line into Video links. Google Drive and Dropbox files must be shared with "Anyone with the link".
- Optional: set the spoken language, pick the output formats, or turn on Add an AI summary.
- Click Start. Short videos take a few seconds each.
- Download the results as JSON, CSV, Excel or HTML, or read them through the Apify API.
How much does it cost?
You pay per result, with no monthly fee:
- $0.02 per video transcribed ($20 per 1,000), covering up to 10 minutes of speech to text. Caption-based transcripts are one event at any length.
- $0.03 per Instagram reel, the same price as our Instagram Reels Transcript Actor.
- $0.006 per extra minute of speech to text after the first 10 minutes of a video.
- $0.005 per AI summary, only when you turn summaries on.
Free rows: unsupported sites, private, deleted or region-locked videos, posts without a video, videos with no audio or no speech (music, silence), YouTube videos without captions, DRM-protected streams, and download or transcription failures are all returned with an error and are never charged.
Free Apify plan: up to 5 videos per run, and speech to text for the first 10 minutes of each. Any paid Apify plan removes these limits. "Max minutes per video" (default 60, up to 180) caps long videos.
Input
{"urls": ["https://www.tiktok.com/@thatdudecancook/video/7649086431641521421","https://x.com/NASA/status/1970856953640530375","https://vimeo.com/76979871","https://archive.org/download/gettysburg_address_librivox/gettysburg_address_lincoln_64kb.mp3"],"language": "auto","outputFormats": ["text", "srt", "vtt", "segments"],"includeSummary": true,"preferCaptions": true}
Output
{"url": "https://x.com/NASA/status/1970856953640530375","platform": "X","author": "NASA","durationSec": 76.89,"transcriptSource": "speech-to-text","language": "en","wordCount": 266,"text": "So, a couple months ago, we thought as a crew, we need to name this spacecraft...","srt": "1\n00:00:00,000 --> 00:00:04,300\nSo, a couple months ago, we thought as a crew, we need to name this spacecraft.\n...","segments": [{ "start": 0, "end": 4.3, "text": "So, a couple months ago, we thought as a crew, we need to name this spacecraft." }],"summary": "A few months ago, the crew of the Orion spacecraft needed to come up with a name for it...","keyPoints": ["..."],"chargedExtraMinutes": 0,"error": null}
Download the dataset as JSON, CSV, Excel, XML or HTML, or fetch it from the API.
Tips
- Single videos only. Profile, channel, playlist, hashtag and folder links are refused for free; use the per-platform Actors linked above for those.
- Language: leave
autofor most videos. Setting a code (es,de,hi...) picks the caption track in that language and helps speech to text on short or noisy clips. It does not translate. - Captions vs speech to text: turn off "Use the platform's captions" if you want Whisper's own transcript of a TikTok or Vimeo video even when captions exist.
- Vimeo: captions are used when the video has them. Vimeo usually protects its streams with DRM, so a Vimeo video without captions often cannot be transcribed (free row). Domain-restricted or private videos are free rows too.
- Direct files: links must point at the file itself (they usually end in .mp4, .mp3, .m4a, .mov, .webm or .m3u8). A link to a web page is a free error row.
FAQ
Which sites are supported?
TikTok, Instagram (reels and video posts), Facebook (videos, reels, fb.watch links), X and Twitter posts, YouTube (captions only), Vimeo, direct video and audio files, HLS (.m3u8) streams, Google Drive and Dropbox files. Other sites get a free error row.
Do I need an account, cookies or an API key?
No. The Actor only reads what each site shows to a logged-out visitor, so private and login-only videos cannot be transcribed.
How accurate is it?
Creator captions are exact. Speech to text uses Whisper large-v3-turbo, which handles clear speech in most languages well; heavy music, crosstalk and very short clips are harder.
How long can a video be?
Speech to text covers up to 180 minutes per video (60 by default). For long recordings, meetings and podcasts our Audio Transcription and Podcast Transcription Actors are built for that job.
Is it legal to transcribe these videos?
It reads public videos only. Check that your use of the transcripts respects copyright and the platforms' terms, and do not use them to collect personal data without a lawful basis.