A 20-slide narrated deck as video: about 71 cents on Sume
20 slides at 15 seconds each: 4,500 characters of narration is $0.21375 on Sume TTS and a 5-minute timeline is $0.50. Assumptions and caption limit.
A narrated deck is mostly audio and layout, not generation. Assume 20 slides, 15 seconds on screen each, so the video is exactly 5 minutes. Assume 225 characters of narration per slide, which is about 15 seconds at 900 characters per minute (an assumption about speech rate, not a measurement). The script is 4,500 characters.
On Sume, TTS is $0.0475 per 1,000 characters, so the narration is $0.21375. The timeline render is $0.10 per output minute, so five minutes is $0.50. Together: $0.71375. Both prices are on the Sume API rate card.
The bill
| Item | Unit price | Quantity | Cost |
|---|---|---|---|
| Text-to-speech | $0.0475 per 1,000 characters | 4,500 characters | $0.21375 |
| Timeline render | $0.10 per output minute | 5 minutes | $0.50 |
| Total | $0.71375 |
Limits that change the plan
TTS accepts up to 20,000 characters per request, so 4,500 fits in one call. The timeline accepts up to 1,800 seconds (30 minutes) of output, so a 5 minute deck is well inside it.
Captions are not in this total. The documented fixed price is $0.20 per job for videos of at most 60 seconds, and a 5 minute deck is longer than that, so check the live price in GET /v1/catalog before you add captions.
For comparison, ElevenLabs lists v4 at $0.022 per 1,000 characters during its promotion through October 12 and $0.08 regular (read 2026-10-05). The same 4,500 characters would be $0.099 promotional or $0.36 regular. Slide images are not priced here; use your own.
- Write to a character budget: 225 characters is about 15 seconds of speech.
- Keep the slide count times seconds equal to the timeline length.
- Check the live caption price for a 5 minute video before you add captions.
Sources
Related posts
More in Pricing
- 2,000 product-name audio clips: 300,000 characters, MAI vs Sume
A catalog of 2,000 spoken product lines at 150 characters costs $4.50 on MAI Flash, $6.60 on MAI-Voice-2.1 and $14.25 on Sume, which cuts one file per line.
- A $25 video model bake-off: one 5-second prompt on six Sume tiers
How many 5-second test clips does $25 buy? From 35 up to 133 runs per tier, per-second Sume rates for Omni Flash, Wan, H3 and Kling 3 Pro.
- 25 six-second product loops: what 480p, 720p and 1080p cost on Sume
A catalog of 25 six-second loops costs $9.375 at Wan 480p and $37.50 at 1080p on Sume. Per-second rates and resolution steps, with fal list prices.
- 30 customer calls of 8 minutes: transcription bill, MAI vs Sume
Thirty recorded calls of 8 minutes is 4 hours of audio: $2.16 on MAI-Transcribe-2-Streaming, $2.40 on Sume STT at 1 cent a minute. One call fits one job.
Written by Sume