Batch Extract Subtitles from Videos

Why this matters

Translation vendors need SRT for every episode, not just one. Batch extraction turns a multi-day manual task into an overnight job.

Per-file jobs mean one difficult episode never blocks the rest of the season.

How it works

Point the API at the folder, set output_format=srt, and poll the batch endpoint. Each file returns its own SRT plus a confidence summary.

Submit a job with an input URL (S3, GCS or HTTPS), poll the job URL, and download the rendered output. No GPU, no queues, no ffmpeg builds to babysit.

Code

import requests, time

API = "https://api.mlslabs.io/v1/subtitle-extractor/jobs"
headers = {"X-API-Key": "YOUR_API_KEY"}
payload = {"input": "s3://bucket/shows/", "output_format": "srt", "pattern": "*.mp4"}

resp = requests.post(API, json=payload, headers=headers)
job = resp.json()
while job["status"] not in ("succeeded", "failed"):
    time.sleep(3)
    job = requests.get(job["url"], headers=headers).json()

print("Output:", job["output_url"])

Pro tips

• Run one episode per show as a smoke test first — fonts differ per title.
• Ship the confidence report to QC, not the raw video.
• Schedule the batch after the episode masters land in S3.

Model the batch extraction in Postman.