Dub 40 nine-minute course lessons into Spanish: up to $54.94

Dubbing 40 nine-minute course lessons into Spanish costs up to $54.94 on Sume, about $1.37 per lesson, at list rates. The render is the biggest line at $0.90 a lesson, and Index-Translate's listed free API handles the translation.

Assumptions: 9 minutes per lesson, 850 characters per minute of speech so 7,650 characters per lesson, and one language. Speech-to-text takes up to 10 minutes of audio per request, so a nine-minute lesson is one request. Rates are from the pricing page, Audio detach docs and Timeline docs, read 2026-10-05.

One lesson, then the course

Each step is captured at its own compute and never above the reservation, so these are ceilings.

Plan the run

Use the lesson number and language in every idempotency key, such as course-l07-es-render, so a rerun reuses finished work. Slides that change between languages may need a new video track, which this bill does not include.

• Source video must be on media.sume.com; import it first.
• Detach takes up to 1,800 seconds of source, so lessons longer than 30 minutes need splitting first.
• Keep each Spanish spine near the lesson length: a spine that speaks past 9:00 adds a billable minute.

Render one lesson

This joins the speech for one lesson for its duration and renders it under the lesson video.

import os, time, requests
API = "https://api.sume.com"
H = {"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"}

def run(path, body, key):
    r = requests.post(API + path, headers={**H, "Idempotency-Key": key}, json=body, timeout=60)
    r.raise_for_status()
    job = r.json()["data"]
    while not requests.get(job["status_url"], headers=H, timeout=30).json()["data"]["terminal"]:
        time.sleep(2)
    res = requests.get(job["result_url"], headers=H, timeout=30)
    res.raise_for_status()
    return res.json()["data"]["result"]

VIDEO, SPEECH = os.environ["VIDEO_URL"], os.environ["SPEECH_URL"]   # both on media.sume.com
joined = run("/v1/timeline-1.0/audio", {"operation": "concat", "parts": [{"url": SPEECH}]}, "dub-0412-de-spine")
secs = joined["duration_seconds"]
body = {"audio": {"url": joined["audio_url"], "duration_seconds": secs},
        "video": [{"source_url": VIDEO, "start": 0, "duration": secs}]}
out = run("/v1/timeline-1.0/render", body, "dub-0412-de-render")
print(out["video_url"])