Transcript
by x402 Video Intelligence in AI models & inference
YouTube video transcript extraction with per-segment timing. Returns the caption track as timed segments (start, duration, text) plus the full plain text, or as SRT subtitles. Uses the creator's manual captions when they exist and falls back to YouTube automatic captions. Never downloads media, so it stays fast and light. Cached per video and language. Use it to summarize a talk, quote a video with timestamps, or search inside video content.
GET https://video.cyberwarex.com/transcript
Last 30 days
Status and outage history · Atom feed
- Uptime
- 100%
- Response time
- 295 ms typical, 375 ms slowest 5%
- Last check
- 31 min ago
- Next check
- any minute now
How to call it
GET https://video.cyberwarex.com/transcript
Each call costs $0.003 in USDC on Base, paid with the request over x402.
Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.
Example request
From the listing.
GET https://video.cyberwarex.com/transcript?format=json&lang=en&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Darj7oStGLkUParameters
| Parameter | Type | Required | Description |
|---|---|---|---|
format | string | No | json returns timed segments; text and srt return text/plain. One of: json, text, srt. Default: "json". |
lang | string | No | Preferred caption language code, e.g. en, es, de. Default: "en". |
url | string (uri) | Yes | YouTube video URL or bare 11-character video id. |
Example response
The provider's example. We can't check it without paying.
{
"lang": "en",
"segments": [
{
"dur": 3.44,
"start": 0.32,
"text": "Welcome back to the channel."
},
{
"dur": 2.88,
"start": 3.76,
"text": "Today we are talking about agents."
}
],
"source": "manual",
"text": "Welcome back to the channel. Today we are talking about agents. ...",
"video_id": "arj7oStGLkU"
}Call it from code
The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.003.
curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i 'https://video.cyberwarex.com/transcript?format=json&lang=en&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Darj7oStGLkU'
# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - 'https://video.cyberwarex.com/transcript?format=json&lang=en&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Darj7oStGLkU' \
| grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decodeJavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";
// Pays at most $0.003 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.003" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);
// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.003 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fvideo.cyberwarex.com%2Ftranscript
const res = await pay("https://video.cyberwarex.com/transcript?format=json&lang=en&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Darj7oStGLkU");
console.log(res.status, await res.text());Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client
# Pays at most $0.003 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.003"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))
with x402_requests(client) as session:
res = session.get("https://video.cyberwarex.com/transcript?format=json&lang=en&url=https%3A%2F%2Fwww.youtube.com%2Fwatch%3Fv%3Darj7oStGLkU")
print(res.status_code, res.text)Security scan
- No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.
Recent checks
| When | Result | HTTP | Time | Price |
|---|---|---|---|---|
| 31 min ago | Passed | 402 | 282 ms | $0.003 |
| 5 h ago | Passed | 402 | 339 ms | $0.003 |
| 9 h ago | Passed | 402 | 247 ms | $0.003 |
| 13 h ago | Passed | 402 | 335 ms | $0.003 |
| 17 h ago | Passed | 402 | 263 ms | $0.003 |
| 20 h ago | Passed | 402 | 239 ms | $0.003 |
| 24 h ago | Passed | 402 | 335 ms | $0.003 |
| 28 h ago | Passed | 402 | 295 ms | $0.003 |
| 32 h ago | Passed | 402 | 375 ms | $0.003 |
| 35 h ago | Passed | 402 | 283 ms | $0.003 |
| 39 h ago | Passed | 402 | 264 ms | $0.003 |
| 42 h ago | Passed | 402 | 298 ms | $0.003 |
| 46 h ago | Passed | 402 | 376 ms | $0.003 |
| 2 days ago | Passed | 402 | 281 ms | $0.003 |
| 2 days ago | Passed | 402 | 360 ms | $0.003 |