TikTok Transcripts - Captions or Speech to Text for Any Video
Pricing
from $6.00 / 1,000 video transcripts
TikTok Transcripts - Captions or Speech to Text for Any Video
Get the transcript of a TikTok video: paste video links and get the spoken words as text with timestamps, from TikTok's captions or, when a video has none, from speech to text. Plus views, likes, comments, author and hashtags. No login. $6 per 1,000 videos (per started 3 min); silent videos free.
Pricing
from $6.00 / 1,000 video transcripts
Rating
0.0
(0)
Developer
Tenfold Fleet
Maintained by CommunityActor stats
0
Bookmarked
1
Total users
0
Monthly active users
10 hours ago
Last modified
Categories
Share
What does TikTok Transcripts do?
TikTok Transcripts gives you the words spoken in any public TikTok video as text. Paste video links, short share links or video ids and get the full transcript, timestamped lines, the language, and the video's views, likes, comments, shares, saves, author, description and hashtags in one row per video.
Not affiliated with TikTok or ByteDance. TikTok is a trademark of ByteDance Ltd.
It works in two steps. First it reads the captions TikTok already has for the video (auto captions, captions the creator edited, or TikTok's own translations). When a video has no captions at all, which is common, it downloads the sound and runs AI speech to text (Whisper) on it, at the same price. Every row says where the text came from in the source field: captions or speech-to-text.
It is a TikTok transcript API that needs no login and no TikTok account. Videos without speech and every failure are free.
Why use a TikTok transcript tool?
- ✍️ Repurpose content: turn TikToks into blog posts, threads, newsletters, scripts and show notes.
- 🔎 Research creators and competitors: read what a brand or creator actually says, search it, and compare scripts of videos with high and low views.
- 🤖 Feed AI pipelines: send transcripts to an LLM for summaries, hooks, topic tags, sentiment or a RAG knowledge base.
- 🌍 Work across languages: get the original language, or TikTok's English translation when the video has one.
- ♿ Subtitles and accessibility: timestamped lines you can turn into SRT or VTT captions.
It runs on the Apify platform, so you also get an API, scheduling, webhooks and integrations with Make, Zapier, n8n, LangChain and LlamaIndex.
What data can it extract?
| Field | Example |
|---|---|
url, videoId | https://www.tiktok.com/@thatdudecancook/video/7649086431641521421, 7649086431641521421 |
authorUsername, authorName | thatdudecancook, Sonny Hurrell |
transcript | the full spoken text |
segments | [{ "start": 0.46, "end": 2.54, "text": "..." }], times in seconds |
source | captions or speech-to-text |
language | en (ISO 639-1 code of the transcript) |
captionLanguage, captionSource | eng-US, auto / creator / translated (for caption transcripts) |
availableCaptions | every caption track the video offers, e.g. [{ "language": "fra-FR", "source": "ASR" }] |
wordCount, durationSec | 224, 69 |
views, likes, comments, shares, saves | 81800, 5114, 56, 354, 975 |
description, hashtags, createdAt | caption text, ["pasta"], 2026-06-08T18:02:21.000Z |
authorFollowers, authorVerified | 4300000, true |
musicTitle, musicAuthor, musicOriginal | the sound used; musicOriginal is false for licensed songs |
noSpeech | true when the video has no spoken words (free) |
chargedVideos | how many video charges the row used (1 for videos up to 3 minutes) |
error | why a video was skipped (deleted, private, photo post, ...), otherwise null |
How to get the transcript of a TikTok video
- Click Try for free.
- Paste links into TikTok video URLs or ids, one per line. Full links,
vm.tiktok.com/vt.tiktok.comshort links and bare ids all work. - Leave Speech to text when there are no captions on to get text for every video, or turn it off for caption transcripts only.
- Optional: set Caption language to
Englishto get TikTok's English translation when a video has one. - Click Start, then download the results as JSON, CSV, Excel or HTML, or read them through the API.
How much does it cost?
$6 per 1,000 videos ($0.006 per transcript), pay per event, speech to text included. You pay the same whether the text came from TikTok's captions or from our speech recognition.
These are free: videos with no speech (music only, silence), deleted or private videos, photo slideshows, links that are not videos, videos TikTok would not show, and any failure.
Videos longer than 3 minutes count once per started 3 minutes (a 7-minute video counts as 3 videos), because longer videos cost more to process. The chargedVideos field shows this on every row. Speech to text covers videos up to 10 minutes; longer videos are transcribed only when TikTok has captions for them.
Free Apify plan: each run transcribes up to 10 videos, and speech to text only runs on videos up to 3 minutes, because every speech-to-text call costs the developer a fee. Other videos in the run come back as free rows with a note. Any paid Apify plan removes these limits.
Input
Output
Download the dataset as JSON, CSV, Excel, XML or HTML from the run page, or fetch it with the Apify API.
Tips
- Turn off Timestamped segments if you only need the text; the full transcript is still there.
captionSourcetells you how the captions were made:autois TikTok's speech recognition,creatormeans the creator edited them,translatedis TikTok's machine translation.- Need a list of videos first? Collect the links with any TikTok profile or hashtag scraper on Apify, then paste them here.
- Set a maximum cost per run in the run options; the Actor stops cleanly when it is reached.
Use it with AI agents (MCP)
Give Claude, ChatGPT, Cursor or any MCP client this Actor as a tool through Apify's MCP server: add https://mcp.apify.com?tools=tenfoldfleet/tiktok-transcripts as a remote MCP server and sign in with your Apify account. The agent fills in the input, runs the Actor and reads the transcripts itself; you pay the same per-event price as a normal run.
FAQ
Do I need a TikTok account or a login?
No. The Actor reads public videos the way a logged-out visitor sees them and never logs in.
What if a video has no captions?
With Speech to text on (the default), the Actor transcribes the video's sound with the Whisper speech model, at the same price. For videos that use their own original sound it reads that sound; for videos with a licensed song it reads the video's audio track, so a voiceover over music is picked up too.
What happens with videos that only have music?
Videos with instrumental music, sound effects or silence normally come back with noSpeech: true and are free. Filler phrases speech models invent on silent stretches (a lone "Thank you.") and sung syllables like "la la la" are removed. Sung lyrics are real words, so a video whose sound is a song with vocals can return the lyrics as its transcript.
Which languages are supported?
Captions come in whatever language TikTok has for the video. Speech to text covers about 100 languages, including English, Spanish, Portuguese, French, German, Indonesian, Arabic, Hindi, Turkish, Russian, Japanese, Korean and Chinese. The language field gives the code.
How accurate are the transcripts?
Caption transcripts are exactly TikTok's captions, so they are as good as TikTok's own speech recognition (or better when the creator edited them). Speech-to-text transcripts are usually close to word for word on clear speech; loud music, crosstalk or noisy audio can cause mistakes, and timestamps are approximate.
Can it transcribe private or deleted videos?
No. They come back as free rows with an error explaining why.
Is it legal to transcribe TikTok videos?
The Actor only processes publicly available videos. You are responsible for how you use the transcripts: respect copyright, TikTok's terms and privacy laws such as the GDPR, and don't process personal data without a legitimate reason. If unsure, ask a lawyer.
