Veo 3.1 — a product film with native sound

curl -X POST 'https://ai.im.inc/api/v1/video/generate' \
  -H "Authorization: Bearer $IMMERSIVE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "image": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/inputs/7724e230-6dc7-4463-bc46-050587cd0129/input_image.png",
  "model": "google/veo-3.1",
  "prompt": "A four-second premium product film from this starting frame, one continuous shot. Preserve the exact warm-pink headphones with the white wave mark, pale circular plinth, charcoal room and diagonal sunlight. A subtle camera slide to the left produces real gentle parallax, a controlled white highlight travels across the curved metal yoke, fine dust glints quietly in the light shaft. The product remains completely still and physically stable on the plinth. Natural perspective, precise material detail, calm confident commercial cinematography. Native sound: a soft airy studio room tone and one restrained warm glassy musical tone that gently fades; no speech or vocals, no loud impacts. Keep the entire product visible throughout. No cuts, no typography, no added objects, no deformation or logo changes.",
  "duration": 4,
  "resolution": "1080p",
  "aspect_ratio": "16:9",
  "generate_audio": true
}'

# Set JOB_ID to the response's "id", then poll every few seconds until the job has finished:
curl "https://ai.im.inc/api/v1/video/$JOB_ID" \
  -H "Authorization: Bearer $IMMERSIVE_API_KEY"

# The finished response has the result at url.

const headers = { Authorization: `Bearer ${process.env.IMMERSIVE_API_KEY}` };

const response = await fetch("https://ai.im.inc/api/v1/video/generate", {
  method: "POST",
  headers: { ...headers, "Content-Type": "application/json" },
  body: JSON.stringify({
    "image": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/inputs/7724e230-6dc7-4463-bc46-050587cd0129/input_image.png",
    "model": "google/veo-3.1",
    "prompt": "A four-second premium product film from this starting frame, one continuous shot. Preserve the exact warm-pink headphones with the white wave mark, pale circular plinth, charcoal room and diagonal sunlight. A subtle camera slide to the left produces real gentle parallax, a controlled white highlight travels across the curved metal yoke, fine dust glints quietly in the light shaft. The product remains completely still and physically stable on the plinth. Natural perspective, precise material detail, calm confident commercial cinematography. Native sound: a soft airy studio room tone and one restrained warm glassy musical tone that gently fades; no speech or vocals, no loud impacts. Keep the entire product visible throughout. No cuts, no typography, no added objects, no deformation or logo changes.",
    "duration": 4,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "generate_audio": true
  }),
});
const job = await response.json();

// Poll every few seconds while the job is still running.
const running = ["pending", "queued", "submitted", "starting", "processing", "running", "streaming", "in_queue", "in_progress"];
let result;
do {
  await new Promise((resolve) => setTimeout(resolve, 5000));
  result = await (await fetch(`https://ai.im.inc/api/v1/video/${job.id}`, { headers })).json();
} while (running.includes(String(result.status).toLowerCase()));

console.log(result.url);

import os
import time

import requests

headers = {"Authorization": f"Bearer {os.environ['IMMERSIVE_API_KEY']}"}

job = requests.post(
    "https://ai.im.inc/api/v1/video/generate",
    headers=headers,
    json={
        "image": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/inputs/7724e230-6dc7-4463-bc46-050587cd0129/input_image.png",
        "model": "google/veo-3.1",
        "prompt": "A four-second premium product film from this starting frame, one continuous shot. Preserve the exact warm-pink headphones with the white wave mark, pale circular plinth, charcoal room and diagonal sunlight. A subtle camera slide to the left produces real gentle parallax, a controlled white highlight travels across the curved metal yoke, fine dust glints quietly in the light shaft. The product remains completely still and physically stable on the plinth. Natural perspective, precise material detail, calm confident commercial cinematography. Native sound: a soft airy studio room tone and one restrained warm glassy musical tone that gently fades; no speech or vocals, no loud impacts. Keep the entire product visible throughout. No cuts, no typography, no added objects, no deformation or logo changes.",
        "duration": 4,
        "resolution": "1080p",
        "aspect_ratio": "16:9",
        "generate_audio": True,
    },
    timeout=300,
).json()

# Poll every few seconds while the job is still running.
running = {"pending", "queued", "submitted", "starting", "processing", "running", "streaming", "in_queue", "in_progress"}
while True:
    time.sleep(5)
    result = requests.get(f"https://ai.im.inc/api/v1/video/{job['id']}", headers=headers, timeout=60).json()
    if str(result.get("status", "")).lower() not in running:
        break

print(result["url"])

{
    "id": "tsbb9q9kjdrmr0d1g6c9xw0m6g",
    "url": "https://s3.eu-central-1.amazonaws.com/ai.im.inc/examples/outputs/7724e230-6dc7-4463-bc46-050587cd0129/result.mp4",
    "status": "succeeded",
    "duration": "4.00",
    "model_name": "google/veo-3.1"
}

Your browser blocked the clipboard. Select the text and copy it by hand.