30-second narrated promo on Sume: four line items, about $0.45
A narrated 30-second promo on Sume prices at about $0.45: TTS for 500 characters, one music track, one caption job and one render minute.
What does a short narrated promo cost on Sume? For a 30-second video with a 500 character script, one music track, burned-in captions and one render, the list prices come to $0.44875, about $0.45. The four line items are TTS, music, captions and a Timeline render.
The prices are from the Sume catalog and docs. Confirm them with GET /v1/catalog (see the API reference) before you budget, because rates are catalog-driven and can change.
The line items
The assumptions are stated so you can swap in your own: a script of 500 characters, one music generation, one standalone caption job on a clip of 60 seconds or less, and a render under one minute.
| Step | Unit | Price per unit | Quantity | Line total |
|---|---|---|---|---|
| Narration, TTS 1.0 | 1,000 characters | $0.0475 | 0.5 | $0.02375 |
| Music, Music Router | Generation | $0.125 | 1 | $0.125 |
| Captions, video captions | Job, up to 60 s | $0.20 | 1 | $0.20 |
| Render, Timeline 1.0 | Output minute, rounded up | $0.10 | 1 | $0.10 |
| Total | $0.44875 |
Where each price comes from
TTS is $0.0475 per 1,000 characters in the catalog. The music price is a fixed $0.125 per generation, whatever the prompt length, per the Music 1.0 docs. The video captions docs state $0.20 per accepted standalone job for videos up to 60 seconds. The Timeline 1.0 docs give $0.10 per ceil of output minute.
What is not in the total
The footage. This total prices the audio, captions and render only; any video or image generation is separate. Joining takes are separate too: a timeline audio concat is a flat $0.01 per job and an audio detach is $0.01 per job, and you only pay them if you use them.
Retries are also outside the line items. Captions on a re-style can reuse the earlier caption's word timings with source_caption_id, which avoids a second speech-to-text pass, but the docs say billing is unchanged, since a restyle is still a render.
Scaling the estimate
For ten promos with the same recipe, the total is ten times $0.44875, or $4.4875. Captions are the biggest line, at about 45 percent of the total, so bundling several short clips into one video of 60 seconds or less can be cheaper than captioning each separately, if your edit allows it.
A longer script moves only the TTS line: 5,000 characters costs $0.2375 instead of $0.02375, taking the total to about $0.66. The other three lines stay put.
Order of operations
Run narration first, since its length decides the render length. Then pick music, assemble on the Timeline, and caption the finished clip so the words match the final audio. The order is walked through in voiceover for shorts: TTS, captions, then timeline.
Sources
Related posts
More in Pricing
- Newsletter writer's monthly media budget on Sume: $2.40
Four weekly issues with a header image, an audio edition and a captioned quote clip cost $2.40 a month on Sume, $28.80 a year, plus $0.60 per extra issue.
- Year-end donor voice messages for 2,000 names: $40 vs $100
Splicing a name clip into a tier message costs $0.02 per donor on Sume, $40 for 2,000 donors, against $100 for a full 900-character message each.
- One 30-second Seedance 2.5 clip or three 10-second clips: price
On Sume a 30-second Seedance 2.5 clip costs the same as three 10-second clips: both are 648,000 tokens at 720p, about $17.33. What differs is retakes.
- 1-hour transcript cost: $0.60 on Sume, two 30-minute files
A 60-minute transcript bills 60 audio minutes at $0.01, so $0.60. Inspect takes 1,800 s files, so cut an hour in two. Rounding example and a year of shows.
Written by Sume