Voice 50 listings at 300 characters each: Sume TTS cost
50 listing scripts of 300 characters each cost $0.7125 on Sume TTS ($0.01425 each). Key each by listing id so a rerun skips finished jobs.

Fifty property-listing voiceovers of 300 characters each cost $0.7125 on Sume TTS, which is $0.01425 per listing at $0.0475 per 1,000 characters. Use the listing id as the Idempotency-Key so a crashed batch can be rerun without paying twice.
Batch cost
Per listing is the tool price for 300 characters; totals multiply it.
| Listings | Per listing | Total |
|---|---|---|
| 10 | $0.01425 | $0.1425 |
| 50 | $0.01425 | $0.7125 |
| 200 | $0.01425 | $2.85 |
| 500 | $0.01425 | $7.125 |
Rerun-safe loop
On a rerun, an identical key and body returns the original job (idempotency_hit true), so the loop is safe to repeat.
listings = [{"id": "L-1041", "text": "Bright two-bedroom..."},
{"id": "L-1042", "text": "Corner studio..."}]
jobs = {}
for item in listings:
jobs[item["id"]] = speak(item["text"], f"listing-{item['id']}-v1")
for lid, job in jobs.items():
print(lid, audio_url(job))Gotchas
Bump the version suffix (v2) when you change a script on purpose; the same key with new text is a 409. Submit all jobs first and poll afterward, as above, rather than waiting on each in turn. Use metadata for the listing id so you can match results later.
Sources
Related posts
More in Use cases
- Which Sume Format for a UGC-style ad? Read io and showcase first
Sume ships ready-made Formats for UGC-style ads. Read each one's io profile and showcase with GET /v1/formats/sume/{slug} before you pick, and cap spend.
- Which Sume video models take 9:16 vertical, and what 10 seconds costs
For 9:16 on Sume: Gemini Omni Flash 1.1, Seedance 2.0 and 2.5. A 10-second 720p vertical clip is $1.25, $3.78 or $5.78. What each model accepts.
- X standalone video lists 16:9 and 1:1: set the Sume render size
Sume timeline renders 1080x1920 by default, but X's standalone video ad spec lists 16:9 and 1:1. Set output width and height to 1920x1080 or 1200x1200.
- X video ad: 2:20 at 6,000 kbps is 105 MB, so the 1 GB cap never binds
X allows 1 GB and 2 minutes 20 seconds. At its recommended bitrate the length limit hits first. The math, plus the 9:55 case for approved advertisers.
Written by Sume