Restaurant daily special clip: Kling 3 with audio, 5 seconds for $1.05

A 5-second daily-special clip with sound is kling-3 with the dish photo as first_frame and generate_audio: true: $1.05 per clip on Sume, against $0.70 silent. A month of 26 specials is $27.30 with audio. Kling Video v3 Pro lists per-second prices with audio off and on, times 1.25 (Video Router, read 2026-10-05).

What goes in the prompt for sound?

Describe the sound you want in plain words (sizzle, clink, soft room tone) alongside the picture, and keep any spoken line short. Check the first clip for sound that does not belong.

curl -X POST https://api.sume.com/v1/videos \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"kling-3","prompt":"Steam rises from the plate, a fork lifts a bite, quiet restaurant ambience with a soft sizzle","duration":5,"resolution":"1080p","aspect_ratio":"9:16","frame_images":[{"type":"image_url","image_url":{"url":"https://example.com/special.jpg"},"frame_type":"first_frame"}],"generate_audio":true}'

What does a month of specials cost?

Kling 3 charges the same per second at 720p and 1080p, so choose 1080p unless the file size matters.

How do I poll and download the result?

A submit returns 202 with id, polling_url, status and model. Poll GET /v1/videos/{id} until status is completed (the other terminal values are failed and cancelled), then download from GET /v1/videos/{id}/content?index=0 with the same bearer key. If you want the audio off, send generate_audio: false and save the difference.

curl https://api.sume.com/v1/videos/JOB_ID -H "Authorization: Bearer $SUME_API_KEY"
curl -L "https://api.sume.com/v1/videos/JOB_ID/content?index=0" \
  -H "Authorization: Bearer $SUME_API_KEY" --output clip.mp4

How do I keep the dish accurate?

Start from a real photo of the dish and ask for small motion only, so the plate in the clip is the plate you serve. See the Kling 3 prompt guide for wording.