Sora 2 Image to Video

Startseite/Entdecken/OpenAI/Sora 2/Image To Video

openai /

OpenAI Sora 2 generates realistic image-to-video content with synchronized audio, improved physics, sharper realism and steerability. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

image-to-video

Eingabe

Enable Safety Checker

Bereit

$0.4pro Durchlauf·~25 / $10

Weiter:

BeispieleAlle anzeigen

Action: The kitten suddenly pounces toward the yarn, batting at it rapidly with its paws, tumbling flexibly, and finally hugging the yarn ball and starting to kick it with its back legs. Ambient Sound: The kitten emits a series of excited "meows" (playful and slightly challenging); the soft "pat-pat-pat" sound of paws hitting the floor and the yarn; the slight shh-shh friction sound as the yarn rolls; the clear, rhythmic tick-tock of a grandfather clock in the room. Character Dialogue: (No human language, only the full range of cat sounds: excited "Mrow! Mrow!", a satisfied purr rumble deep in its throat after catching the "prey," and a tiny hiss of exertion.)

The camera zooms in to the sweat of the characters, and the surrounding atmosphere is tense.

README

Sora 2 Image-to-Video

Notice — Service Stability

The Sora 2 family is currently unstable. Generations may fall back to alternative models without notice and the service can be temporarily unavailable. OpenAI is also expected to discontinue this model in the future.

If you need an equally capable, stable alternative, we recommend Seedance 2: bytedance/seedance-2.0/image-to-video.

OpenAI Sora 2 Image-to-Video

Sora 2 Image-to-Video brings your images to life with OpenAI's state-of-the-art video generation. Upload an image and describe the motion — watch as AI transforms your still photo into a dynamic, cinematic video with synchronized audio.

Why Choose This?

Image animation Transform any still image into smooth, realistic video with natural motion.
Physics-aware motion Learns contact, inertia, and momentum so objects move and collide believably.
Synchronized audio Generates matching audio — ambient sounds, dialogue, and sound effects.
Temporal consistency Stable identities, minimal flicker/ghosting, and clean frame-to-frame transitions.
Cinematic quality Natural camera movements, high-frequency detail, and professional-grade output.
Flexible duration Generate videos from 4 to 20 seconds.

Parameters

Parameter	Required	Description
image	Yes	Source image to animate
prompt	Yes	Describe the motion, action, and audio cues
duration	No	Video length: 4, 8, 12, 16, or 20 seconds

How to Use

Upload your image — the still photo you want to animate.
Write your prompt — describe the action, motion, camera movement, and audio.
Set duration — choose 4, 8, 12, 16, or 20 seconds.
Submit — generate, preview, and download your video.

Pricing

Duration	Cost
4 s	$0.40
8 s	$0.80
12 s	$1.20
16 s	$1.60
20 s	$2.00

Billing Rules

Rate: $0.10 per second
Duration options: 4, 8, 12, 16, or 20 seconds

Best Use Cases

Photo animation — Bring still photos to life with realistic motion.
Product showcases — Animate product images for dynamic marketing.
Art animation — Transform illustrations and artwork into videos.
Social media content — Create eye-catching animated posts from images.
Storytelling — Build narratives from key visual moments.

Pro Tips

Be specific about motion in your prompt: "The kitten pounces toward the yarn" beats "kitten playing."
Include audio cues in your prompt for better synchronized sound.
Higher resolution source images produce better results.
Describe camera movement if you want dynamic cinematography.
Start with shorter durations to test your prompt before generating longer videos.

Notes

Image and prompt are both required fields.
Duration options: 4, 8, 12, 16, or 20 seconds.
Please follow OpenAI's usage policies: What images are permitted and prohibited in Sora-2

Related Models

Sora 2 Text-to-Video — Generate videos from text prompts.
Sora 2 Characters — Create reusable character IDs.
Sora 2 Pro Image-to-Video — Premium quality with more resolution options.

Barrierefreiheit:Diese Website nutzt KI-Modelle von Drittanbietern.

Sora 2 Image To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/openai/sora-2/image-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Sora 2 Image To Video below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/openai/sora-2/image-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "duration": 4
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("openai/sora-2/image-to-video", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "image": "https://example.com/your-input.jpg",
        "duration": 4
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "openai/sora-2/image-to-video",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "image": "https://example.com/your-input.jpg",
    "duration": 4
}
)

print(output["outputs"][0])  # → URL of the generated output

Sora 2 Image To Video API — Frequently asked questions

What is the Sora 2 Image To Video API?

Sora 2 Image To Video is a OpenAI model for video generation from images, exposed as a REST API on WaveSpeedAI. OpenAI Sora 2 generates realistic image-to-video content with synchronized audio, improved physics, sharper realism and steerability. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Sora 2 Image To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/openai/openai-sora-2-image-to-video.

How much does Sora 2 Image To Video cost per run?

Sora 2 Image To Video starts at $0.40 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Sora 2 Image To Video accept?

Key inputs: `prompt`, `image`, `duration`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/openai/openai-sora-2-image-to-video.

How long does Sora 2 Image To Video take to generate?

Average end-to-end generation time on WaveSpeedAI is around 127 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Sora 2 Image To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (OpenAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.