OpenAI Sora 2 Pro is a state-of-the-art text-to-video model with realistic physics, synchronized audio, and strong steerability. Supports multiple resolutions up to 1080p and durations up to 20 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Ожидание
$1.2за запуск
Interrogation room, single overhead bulb. A detective slaps a folder on the table and says, "We already know you were there." The suspect looks up slowly, smirks, and replies, "Then why are you still asking?" Tight cross-cutting between faces, high contrast, Fincher-esque.
Two old friends sit across from each other at a small café table, warm afternoon light through dusty windows. One leans forward and says, "I never told you, but that day changed everything for me." The other goes quiet, looks down at their cup, then slowly nods. Handheld camera, intimate framing, film grain.
A couple stands under a streetlight in the rain. She turns away, arms crossed. He reaches out and says, "Just tell me what you want me to say." She spins around, eyes wet — not just from rain — and says, "I want you to mean it." Silence. Medium shot, cold blue tones, slow zoom in.
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/text-to-video.
Sora 2 Pro is OpenAI's premium video and audio generator. It advances prior video models with more accurate physics, sharper realism, synchronized audio, stronger steerability, and a wider stylistic range — built on the original Sora foundation.
Now with character consistency — create reusable character IDs and feature them across multiple videos with the same identity.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe scene, style, camera, and audio cues |
| size | No | Output resolution (see options below) |
| duration | No | Video length: 4, 8, 12, 16, or 20 seconds |
| characters | No | List of character IDs for consistent identity |
| Duration | 720p | 1024p | 1080p |
|---|---|---|---|
| 4 s | $1.20 | $2.00 | $2.80 |
| 8 s | $2.40 | $4.00 | $5.60 |
| 12 s | $3.60 | $6.00 | $8.40 |
| 16 s | $4.80 | $8.00 | $11.20 |
| 20 s | $6.00 | $10.00 | $14.00 |
Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/openai/sora-2-pro/text-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Sora 2 Pro Text To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 4
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/openai/sora-2-pro/text-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/openai/sora-2-pro/text-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 4
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
`https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"size": "1280*720",
"duration": 4
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/openai/sora-2-pro/text-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout"}:
raise RuntimeError(result)
if status not in {"created", "processing"}:
raise RuntimeError(f"Unexpected status: {status}")
time.sleep(2)Sora 2 Pro Text To Video is a OpenAI model for video generation, exposed as a REST API on WaveSpeedAI. OpenAI Sora 2 Pro is a state-of-the-art text-to-video model with realistic physics, synchronized audio, and strong steerability. Supports multiple resolutions up to 1080p and durations up to 20 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
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 result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/openai/openai-sora-2-pro-text-to-video.
Sora 2 Pro Text To Video starts at $1.20 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.
Key inputs: `prompt`, `duration`, `size`, `characters`. 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-pro-text-to-video.
Median end-to-end generation time on WaveSpeedAI is around 291 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
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.