Kling 3 native audio: what the on and off price difference is

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?

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.