Kling 3 native audio: what the on and off price difference is
On Sume, kling-3 costs $0.14 a second silent and $0.21 with audio. Audio is on unless you send generate_audio false, so the default is the higher price.

On Sume, kling-3 reserves $0.14 per second with generate_audio: false and $0.21 per second with audio, both before a default 5.5% agent fee. The catch is the default: when you leave generate_audio out, audio is on, so you pay the higher rate. Send false when you will add your own music or voice.
Sume numbers are from the pricing code behind Video generation, read 2026-09-29. Kling's capability map lists native audio for Kling 3.0 and Turbo.
How much is a clip with and without audio?
| Duration | Silent | With audio |
|---|---|---|
| 4 s (minimum) | $0.56 | $0.84 |
| 5 s | $0.70 | $1.05 |
| 10 s | $1.40 | $2.10 |
| 15 s | $2.10 | $3.15 |
How do I turn audio off?
Send generate_audio: false. Omitted, it follows the model's audio capability, which is on for kling-3.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: kling-silent-001" \
-d '{
"model": "kling-3",
"prompt": "Product on a turntable, soft studio light.",
"duration": 5,
"generate_audio": false
}'Is the audio worth the extra?
It depends on where the clip goes. For a clip you will score with your own music or voice-over, silent is enough. For a clip with ambient sound or speech that must match the picture, audio on avoids a second step. Kling's map shows native audio supported for Kling 3.0 but voice control (human voice) not supported, so don't count on a specific voice.
Where do I see what I paid?
The poll response's usage.cost is the Sume billable amount for the job, per the docs; Usage in the dashboard shows the rest.
Sources
Related posts
More in Models
- Lyria 3 Pro or Lyria 3.5: which model id do I send?
Sume's Music Router accepts sume/music-auto, lyria-3.5 and lyria-3-pro. What each id does, how to pin one, and what Google lists for the models.
- Lyria 3.5 API: model id, request and how to call it
Lyria 3.5 is in the Gemini API as lyria-3.5. Here is what Google's page says about it and how to call it from Sume with one music request.
- AI music generator with vocals: Lyria 3.5 lyrics by API
Lyria 3.5 can sing. How to ask for vocals or an instrumental, steer lyrics with section tags, and read the lyrics back from a Sume music job.
- Lyria 3.5 release date: where it is available
Google announced Lyria 3.5 in the Gemini app on 2026-09-04. Where Google says you can use it, and where Sume lists it.
Written by Sume