47-second voiceover: Gemini 3.8 Flash TTS vs Sume TTS

A 47-second voiceover rounds to 50 seconds on Gemini 3.8 Flash TTS: $0.01125 now, double from 2027-01-01. Sume TTS charges $0.0475 per 1,000 characters.

5 min readSume
All posts

A 47-second voiceover costs about $0.011 on Gemini 3.8 Flash TTS today and about $0.034 on Sume TTS, so Google is the cheaper of the two for speech alone. Google states that its Flash TTS prices double on January 1, 2027, which is the date to put on your calendar if you plan a long-running job on this model.

How each is billed

Google quotes $0.00225 per 10 seconds of generated audio on the standard tier, alongside $0.50 per million input text tokens and $9.00 per million audio tokens. Those token rates apply through December 31, 2026. Sume bills by character: $0.0475 per 1,000 characters, with a one-cent minimum per job and a $0.95 maximum request (20,000 characters).

47-second voiceover, read 2026-10-09 (Google pricing page, Sume catalog)
RouteBasisCost
Gemini 3.8 Flash TTS, standard, now5 blocks of 10 s x $0.00225$0.01125
Gemini 3.8 Flash TTS, batch, now5 blocks x $0.001125$0.005625
Gemini 3.8 Flash TTS, standard, from 2027-01-01doubled$0.0225
Sume TTS, assumed 705 characters705 / 1000 x 0.0475$0.033487

The assumption in the table

Speech speed varies by language and voice, so the Sume row assumes 15 characters per second: 47 x 15 = 705 characters. That is an assumption, not a Sume figure. Replace it with the real character count of your script and the Sume row scales linearly. Rounding 47 seconds up to five 10-second blocks on the Google side is also an assumption about how partial blocks bill, chosen to avoid understating the cost.

What to weigh besides price

At these volumes the price difference is a fraction of a cent per voiceover, so the decision is about the surrounding workflow. Sume returns TTS as an async job you poll at GET /v1/jobs/:id/status, and the audio can go straight into a Timeline job as the audio spine, billed at $0.10 per output minute. If you only need raw speech files, Google's model is the cheaper path through the January cutoff.

Both vendors change prices. Read the Gemini API pricing page and the Sume catalog before you commit to a budget.

  • Speech only, short clips: Google is cheaper per voiceover.
  • Speech feeding a rendered video: Sume keeps TTS and Timeline on one balance.
  • Budget for the 2027-01-01 doubling if you stay on Google's Flash model.

Reproduce the numbers

Every Sume price on this page comes from the public catalog at https://api.sume.com/v1/catalog, which needs no API key. Fetch it, find the row for the job or model named in the table, and multiply by your own seconds, characters or image count. Sume bills the list price shown in that row, so the catalog figure is the one that applies to your balance.

Vendor figures were read from Google Gemini API pricing on 2026-10-09 and are the vendor's to change. Where a vendor page did not show a number, this page leaves it out instead of guessing, and any assumption that is ours is labeled as one.

Sources

Related posts

More in Comparisons

All Comparisons posts

Written by Sume