Kling 3 Pro native audio costs 7 cents more per second on Sume
Kling 3 Pro on Sume is $0.14/s with audio off and $0.21/s with audio on, a 50% premium. Ten-second cost, fal list prices and what Kling 4.0 has not priced.

Native audio is the line item that changes a Kling 3 Pro bill most. On Sume, Kling 3 Pro is billed at $0.14 per second with audio off and $0.21 per second with audio on. Sume prices are the provider list price times 1.25, so the audio premium is $0.07 per second, or 50 percent. The video generation docs describe how a request is reserved at submit and settled to the actual amount.
On fal, the Kling 3.0 Pro page lists $0.112 per second with audio off and $0.168 with audio on (read 2026-10-05). It also lists $0.196 per second for audio with voice control. That third tier is a fal price; this post does not claim a Sume equivalent for it.
What a clip costs
Multiply the rate by seconds. A 10 second clip is $1.40 with audio off and $2.10 with audio on. A 5 second clip is $0.70 versus $1.05.
| Clip length | fal audio off | Sume audio off | fal audio on | Sume audio on |
|---|---|---|---|---|
| 5 s | $0.56 | $0.70 | $0.84 | $1.05 |
| 10 s | $1.12 | $1.40 | $1.68 | $2.10 |
| 15 s | $1.68 | $2.10 | $2.52 | $3.15 |
When the premium is worth paying
Pay it when the clip ships as-is and the sound is part of the shot: dialogue, ambient sound, a product demo with a click. Skip it when you will replace the track anyway with a voiceover or music, because you would pay for audio you discard.
If you plan to add narration separately, TTS on Sume costs $0.0475 per 1,000 characters, so a short voiceover is cheaper than the audio premium on a long clip. Generate silent, then layer sound in a timeline.
- Decide audio per clip before you submit; the rate is set by the request.
- Draft at audio off, then rerun only the keepers with audio on.
- Budget the final run, not the draft, at the audio-on rate.
What about Kling 4.0
Kling published a Kling 4.0 versus 3.0 comparison covering clips up to 30 seconds, 10-bit HDR at 1080p and 4K, and up to 10 keyframes, with Flash in early access and the full launch due in October. The page lists no price, so there is nothing to compare yet. Until a vendor price exists, budget from the Kling 3 Pro rates above and read the live rate through the catalog call below.
import os
import requests
resp = requests.get(
"https://api.sume.com/v1/videos/models",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
timeout=30,
)
resp.raise_for_status()
for model in resp.json()["data"]:
print(model["id"], model["supported_durations"], model["pricing_skus"])
Sources
Related posts
More in Pricing
- Kling 3.0 voice control is $0.196 a second on fal; Sume has two rates
fal lists Kling 3.0 Pro at $0.112 silent, $0.168 with audio and $0.196 with voice control. Sume bills kling-3 at $0.14 or $0.21 a second, with no voice control.
- Kling motion control cost calculator: ceil(seconds) x $0.1575
Sume bills Kling motion control as ceil(duration_seconds) x $0.1575. A four-line Python function prices 5, 12.4, 15 and 30 second references before you submit.
- Kling motion control duration_seconds 1: shortest clip is $0.1575
Kling motion control on Sume takes a 1-second reference, so a probe costs $0.1575. kling-3 starts at 4 seconds ($0.56 silent). Test before you pay for 30 s.
- Largest single AI video job each Sume model allows, by price
The most one Sume video job can reserve ranges from $1.13 on H3 to $42.65 on Seedance 2.5 at 30 seconds and 1080p. Eleven rows.
Written by Sume