AnyAPI / TikTok Video Transcript (native captions)

AnyAPI tool anyapi-run-tiktok-video-transcript on looot: input fields, $0.002 per call, output shape, and code to run it with curl, JavaScript or Python.

Fetch the caption track TikTok itself published for a video, as TikTok wrote it. It is the cheapest way to get the words, and it is only as good as TikTok’s own transcription: it mishears names and uncommon words, and many videos - especially non-English ones - have no caption track at all, which comes back as not found. When you need the words to be right, or there is no track to read, tiktok.video_transcript_full transcribes the audio with AnyAPI’s own speech-to-text instead. Price: $1.20 per 1,000 requests (flat per request - same cost regardless of results returned). Routing: 2 independent lanes are available in execution order. A failed attempt uses the next lane only when the request’s payment authorizes that lane’s price; the normalized schema stays the same. Catalog: TikTok Video Transcript (native captions) pricing and uptime - live USD price, lane routing, and measured 30-day uptime. Every TikTok endpoint.

• Tool id: anyapi-run-tiktok-video-transcript
• Provider: AnyAPI
• Job: Transcribe a video from its URL (video.transcript.get)
• Price: $0.002 per call. A call that fails at the provider costs $0.

Inputs

Output

The run’s result holds the provider’s answer. Signed in, looot inspect anyapi-run-tiktok-video-transcript prints its fields.

Run it

Every call needs your API token in LOOOT_TOKEN; Sign in shows how to get one. Each run also needs a new idempotency key, so a retry never pays twice. With wait: 30 the answer comes back inline when the run ends within 30 seconds. Otherwise you get the running run back: poll GET /v1/runs/<runId>.

Example input with placeholder values:

curl -X POST "https://api.looot.ai/v1/runs" \
  -H "Authorization: Bearer $LOOOT_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{"endpointId":"anyapi-run-tiktok-video-transcript","input":{"url":"https://example.com"},"wait":30}'

const response = await fetch("https://api.looot.ai/v1/runs", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.LOOOT_TOKEN}`,
    "Content-Type": "application/json",
    "Idempotency-Key": crypto.randomUUID(),
  },
  body: JSON.stringify({
    endpointId: "anyapi-run-tiktok-video-transcript",
    input: {
      url: "https://example.com",
    },
    wait: 30,
  }),
});
const run = await response.json();
console.log(run.status, run.result);

import os
import uuid

import requests

response = requests.post(
    "https://api.looot.ai/v1/runs",
    headers={
        "Authorization": f"Bearer {os.environ['LOOOT_TOKEN']}",
        "Idempotency-Key": str(uuid.uuid4()),
    },
    json={
        "endpointId": "anyapi-run-tiktok-video-transcript",
        "input": {
            "url": "https://example.com",
        },
        "wait": 30,
    },
    timeout=90,
)
run = response.json()
print(run["status"], run.get("result"))

To let looot pick among every provider of this job instead, send job:video.transcript.get as endpointId; see the job page.