Video Transcript & Translation: YouTube, TikTok, Reels to Text
Pricing
from $6.00 / 1,000 video transcripts
Video Transcript & Translation: YouTube, TikTok, Reels to Text
Video to text: transcripts and SRT/VTT subtitles of YouTube, TikTok, Instagram Reels, Facebook and X videos; translate them into Ukrainian and 20 more languages in the same run (multilingual). Captions first, Whisper speech to text when there are none. Failed videos are free. No API key.
Pricing
from $6.00 / 1,000 video transcripts
Rating
0.0
(0)
Developer
Andriy Kuzmenko
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 days ago
Last modified
Categories
Features
Share
Video Transcript & Translation: YouTube, TikTok, Instagram, Facebook
Paste video links, get the transcript, timestamped segments, SRT / VTT subtitles and an optional translation - for YouTube videos and Shorts, TikTok, Instagram Reels, Facebook videos and Reels, X (Twitter), Vimeo and 1,000+ other sites.
What makes it different
- Translation into Ukrainian and 20 other languages in the same run. You get the translated transcript and ready-to-use SRT/VTT subtitles for it, not only for the original. Of the transcript Actors we found in the Apify Store (October 2026), only one other offers translation, at $0.045 / $0.013 per video. Here it costs from $0.007 per minute. Languages: English, Ukrainian, Russian, German, French, Spanish, Portuguese, Italian, Polish, Dutch, Turkish, Czech, Romanian, Swedish, Arabic, Hindi, Indonesian, Vietnamese, Chinese, Japanese, Korean.
- All platforms in one Actor. One input list takes YouTube videos and Shorts, TikTok, Instagram Reels, Facebook videos and Reels, X (Twitter), Vimeo and 1,000+ other sites. Most alternatives cover one platform per Actor.
- Works when there are no captions. Captions are used first: fast, any length, one flat price. Without them the speech is recognised with Whisper large-v3, so TikToks, Reels and YouTube videos without captions still get a transcript. Many YouTube transcript tools return nothing in that case.
- Failed videos are free. Private, deleted, blocked or too-long videos get an
errorfield and are not charged. You pay only for the transcripts you receive. - No API key of your own. You don't need an OpenAI or any other account: you pay per video through Apify.
Also included: timestamped segments, SRT and VTT subtitle files with download links, and the video's title, author, upload date, duration and views next to the text. Speech recognition covers 99 spoken languages, including Ukrainian. Recognition in Ukrainian is common; what is rare is translation into Ukrainian and the other languages.
Input
{"videoUrls": ["https://www.youtube.com/watch?v=MLgYJh6OFbY","https://www.tiktok.com/@nasa/video/7698805564884733198"],"translateTo": "es","useCaptions": true,"maxDurationMinutes": 60}
| Field | Meaning |
|---|---|
videoUrls | Links to single videos. Profile, playlist and search pages are not supported. |
translateTo | Optional language code (en, es, de, uk…) to also translate the transcript and subtitles |
language | Spoken language code, or empty to detect it automatically |
vocabulary | Names and terms said in the videos, to spell them correctly (speech recognition only); Ukrainian city names are built in when language is en, uk or ru |
useCaptions | Use the video's captions when available (default). Off: always recognise the speech with Whisper |
maxDurationMinutes | Videos without captions longer than this are skipped (free). Captions work for any length |
quality | accurate (Whisper large-v3, default) or fast (large-v3-turbo) - same price |
crossCheck | Speech recognition only: recognise the audio again with the other model and list where the two disagree (see below). Doubles the recognition price |
subtitles | Save SRT and VTT files (free) |
includeSegments | Include timestamped segments, not only the full text |
Output
{"url": "https://www.tiktok.com/@nasa/video/7698805564884733198","platform": "tiktok","title": "…","author": "nasa","uploadDate": "20261020","durationSeconds": 45,"language": "en","transcriptSource": "speech-recognition","text": "…","segments": [{ "start": 0.0, "end": 3.2, "text": "…" }],"srtUrl": "https://api.apify.com/v2/key-value-stores/.../records/0001-7698805564884733198.srt?signature=...","vttUrl": "https://api.apify.com/v2/key-value-stores/.../records/0001-7698805564884733198.vtt?signature=...","translation": { "language": "es", "text": "…", "segments": [], "srtUrl": "…", "vttUrl": "…" }}
transcriptSource is uploaded-captions, automatic-captions or speech-recognition.
Missed speech (gaps)
Whisper sometimes skips a sentence or two: the transcript reads smoothly, but a few seconds of speech are not in it, or are a single word («The» for seven seconds). Every transcript is checked for this, free of charge. Each stretch of 5 seconds or more with no text, or almost none, is measured with ffmpeg; where it holds sound and not silence, it is recognised again on its own. The item then lists these places:
"gaps": [{ "start": 18.8, "end": 25.4, "status": "filled", "text": "next shipment of cement and steel rods is planned..." },{ "start": 61.0, "end": 70.2, "status": "unclear", "text": "" }]
filled: the speech was found and is now in text, segments and the subtitles. unclear: there is sound but no
clear speech was found (music, noise, crosstalk), worth listening to. No gaps field: nothing was missed.
Cross-check: where to listen again
Wind, music and crowd noise break numbers and short words first, and the two Whisper models break them differently.
With "crossCheck": true the same audio is recognised by the second model as well, and the item gets the places where
the two transcripts disagree. A real run on a BBC weather report recorded in a storm:
"crossCheck": {"model": "whisper-large-v3-turbo","agreement": 0.884,"differences": [{ "start": 0.0, "end": 7.0, "text": "gusts of wind of 17 even 18", "other": "just a room of 70 even 80", "numbers": true },{ "start": 21.0, "end": 28.0, "text": "with drought in", "other": "throughout", "numbers": false }],"text": "…the full transcript of the second model…"}
The turbo figures match the Met Office forecast for that day (gusts of 60-70 mph, up to 80), and «throughout the
morning» fits the sentence; turbo in turn misheard «gusts of wind of». Each model was wrong in a different place.
numbers: true marks the differences with figures in them, the ones that matter most. Times come from the main
transcript. Where both models agree they can still both be wrong, so this narrows the listening down, it does not
replace it. Videos with captions are not cross-checked.
Pricing
You pay per result. On any paid Apify plan you get the lower price.
| Event | Free plan | Paid plans | What counts |
|---|---|---|---|
video | $8 / 1,000 | $6 / 1,000 videos | one transcript, from captions (any length) or up to 3 minutes of recognised speech |
audio-minute | $5 / 1,000 | $4 / 1,000 minutes | speech recognition only (TikTok, Instagram, Facebook, X…): each started minute after the first 3 |
youtube-audio-minute | $12 / 1,000 | $10 / 1,000 minutes | YouTube videos without captions: each started minute, charged instead of video |
translated-minute | $10 / 1,000 | $7 / 1,000 minutes | only with translateTo: each started minute of translated video (text and subtitles) |
Examples on a paid plan:
- a YouTube video with captions: $0.006, whatever its length;
- a 1-minute TikTok: $0.006;
- the same TikTok translated into Ukrainian: $0.013;
- a 10-minute YouTube video without captions: $0.10;
- a 1-minute TikTok with
crossCheck: $0.012 (the recognition events are charged twice).
Each run also carries Apify's standard start fee of $0.05 per 1,000 runs. Subtitles are free. If a run reaches your maximum charge, the remaining videos are skipped.
Privacy
Audio is sent to Groq's speech-to-text API (Whisper) only when a video has no captions; transcripts are sent to Groq's language model API only when you ask for a translation. See Groq's privacy policy. Results stay in your own Apify run storage. Transcribe only videos you are allowed to use.
Guides
- YouTube subtitles in Ukrainian - transcript and translated SRT by API
- MCP server for document and media tools - OCR, PDF and audio tools for Claude or Cursor
Related Actors
- Audio & Video Transcriber - your own audio and video files to text and subtitles
- Text to Speech · Video Frame Extractor
Use with AI agents and code
- MCP (Claude, Cursor, VS Code, any MCP client): add
https://mcp.apify.com?tools=ai_admin/social-video-transcriptas an MCP server - the agent gets one tool with this Actor's input schema and pays per use through your Apify account. - One HTTP call that returns the results:
curl -X POST "https://api.apify.com/v2/acts/ai_admin~social-video-transcript/run-sync-get-dataset-items?token=$APIFY_TOKEN" \-H "Content-Type: application/json" \-d '{"videoUrls": ["https://www.tiktok.com/@nasa/video/7698805564884733198"], "translateTo": "es"}'
Limits
- Private videos, videos that need a login and live streams are not supported.
- Instagram often blocks downloads from servers; such Reels get an
errorand are free. - Speaker labels (diarization) are not included.