60-second spot on Sume: six Wan clips, voice, music, render cost split

A 60-second spot made of six 10-second Wan 3.0 clips at 720p, a voiceover, a music bed and a Timeline render costs $7.76775 on Sume, and the voiceover is 0.6% of it. Switching to a cheaper speech vendor changes the total by cents.

Line items

Prices are from the Sume catalog. The voiceover assumes 15 characters per second, 900 characters for 60 seconds; that is an assumption, not a Sume figure.

Swapping the voice vendor

Gemini 3.8 Flash TTS lists $0.00225 per 10 seconds of audio on Google's pricing page, so 60 seconds is $0.0135. Replacing Sume's voiceover with it saves $0.02925, leaving a total of $7.7385. Google's price doubles on 2027-01-01. The saving is real but small beside the $7.50 of video.

The video line is where the budget sits. Moving the clips to 1080p adds $7.50, and moving to Seedance 2.5 at 720p makes the clips $34.668.

Where to spend time instead

Since voice and music together are about $0.16775, spend effort on the clips: draft at 480p ($0.0625 a second, $3.75 for all 60 seconds), then re-render only the clips you keep. The Timeline job takes an audio spine of 1 to 1,800 seconds and 1 to 200 video slots, so reordering or replacing a single clip does not mean regenerating the others. See the Timeline page and the Video generation page.

Check Google's pricing page and Sume's catalog before you quote a figure to a client.

• Video is roughly 97% of this spot's cost.
• Draft at 480p, final at 720p or 1080p.
• Voice vendor choice is a cents-level decision here.

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.