Openai Sora 2 Pro Text To Video API Documentation

Openai Sora 2 Pro Text To Video API Documentation

Playground

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.

Features

> Notice — Service Stability > > The Sora 2 family is being retired or has already been retired by its original provider. Until it is fully removed, the service is unstable: generations may fall back to alternative models without notice, results can differ from what this model used to produce, and the service can be temporarily unavailable. > > If you need an equally capable, stable alternative, we recommend Seedance 2: bytedance/seedance-2.0/text-to-video.

OpenAI Sora 2 Pro 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.

Why It Looks Great

• Physics-aware motion: learns contact, inertia, and momentum so objects move and collide believably.
• Temporal consistency: stable identities, minimal flicker/ghosting, and clean frame-to-frame transitions.
• Synchronized audio: lip-sync alignment, beat-aware cuts, and ambience that matches on-screen action.
• High-frequency detail: preserves fine textures (skin, fabric, foliage) without plastic over-sharpening.
• Complex scene reasoning: handles multiple subjects, occlusions, depth, and long camera moves coherently.
• Cinematic camera literacy: natural pans, push-ins, and handheld vibes without warping or jelly-artifacts.
• Wide stylistic range: from photoreal and documentary to anime, 3D, and illustrative aesthetics.
• Strong steerability: responds predictably to prompt edits and control settings (duration, fps, motion strength).

Parameters

Size Options

• 720×1280 / 1280×720 (720p)
• 1024×1792 / 1792×1024 (1024p)
• 1080×1920 / 1920×1080 (1080p)

How to Use

1. Write your prompt — describe scene, style, camera movement, and audio cues.
2. Select size — choose resolution and orientation.
3. Set duration — select 4, 8, 12, 16, or 20 seconds. 4.5. Submit — generate, preview, and download when ready.

Pricing

Billing Rules

• 720p rate: $0.30 per second
• 1024p rate: $0.50 per second
• 1080p rate: $0.70 per second
• Duration options: 4, 8, 12, 16, or 20 seconds

Notes

• Prompt is the only required field.
• Please follow OpenAI’s usage policies: What images are permitted and prohibited in Sora-2

Related Models

• Sora 2 Text-to-Video — Standard version at lower cost.
• Sora 2 Pro Image-to-Video — Animate images with Sora Pro quality.

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "size": "1280*720",
  "duration": 4
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/openai/sora-2-pro/text-to-video" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters