Videos to text

Videos to text runs on 7 platforms: the example run makes 1 calls and costs at most $0.0020.

Gets the transcript of each video by its link, as one table: link, language, full text. Every video is one call charged on its own; a video without a transcript is not charged and is left out. A summary is for your own agent to write.

Tell your AI

Install the DataXAPI skill dataxapi-transcripts from https://dataxapi.com/skills/dataxapi-transcripts.zip.

Download the packageA .zip with one SKILL.md. It runs with the dataxapi command line.SKILL.md →

Not connected yet? Connect your AI first →

Example run$0.0020at most. A failed call is never charged
Calls1with the example inputs
Platforms+37 · the same table from each
Hard ceiling10 callsno run is opened above $0.0500

Ask it like this

Any wording works. Three to start from.

What does this TikTok video say? Give me the full transcript.
Turn these five YouTube links into text and summarise each one in two lines.
Get the transcripts of these videos and list every product they mention.

What it does

Four steps. Only the second calls endpoints, so only the second costs money.

Show the plan first

Free, and needs no key: the most calls and the most money this run can come to.

dataxapi run transcripts platform=tiktok links=https://www.tiktok.com/@nasa/video/7665840565958872333 --plan

Run it, capped at that amount

Each line is one endpoint of the example run, at its listed price.

1 callat most $0.0020A call that fails is not charged. The run stops rather than spend more than its cap.
dataxapi run transcripts platform=tiktok links=https://www.tiktok.com/@nasa/video/7665840565958872333 --yes --max-spend 0.002 --out transcripts.csv

Line everything up in one table

3 columns, the same on every platform; a column a platform does not give is empty. No call, no cost.

Your AI reads the table and answers

What the table means is for your AI to say. It ends with where the data came from and when.

What you get back

An illustration of the table, with the task's real columns. The names and figures in it are made up.

Your AIVideos to text
sample

What does this video say?

LinkLanguageTranscript
https://www.tiktok.com/@trailbrew/video/…enOkay, so we are at twenty-four hundred metres, and water boils at ninety-two degrees up here…
https://www.tiktok.com/@summitcup/video/…enThree things under fifteen dollars that changed my camp coffee. Number one…

All 3 columns: link Link, lang Language, text Transcript

1 call · at most $0.0020Trends and topics

Inputs it needs

Say them in your question, or let your AI ask.

platform one platform

The platform the videos are on. Example: tiktok

links list, up to 10

Links to the videos, at most 10. Example: https://www.tiktok.com/@nasa/video/7665840565958872333

The 7 endpoints it uses

One per platform and step. Each has a page with its parameters, fields and price.

Show all 7 endpoints →

Platforms it runs on

Run it on your own question.

Seeing the plan is free. A failed call is never charged.

Start free