Openai Sora 2 Text To Video Pro API Documentation

Openai Sora 2 Text To Video Pro API Documentation

Playground

OpenAI Sora 2 Text-to-Video Pro creates high-fidelity videos with synchronized audio, realistic physics, and enhanced steerability. 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.

Sora 2 Text-to-Video Pro

Sora 2 Text-to-Video Pro is OpenAI’s premium text-to-video model. Describe any scene in natural language — AI renders it into a cinematic, high-resolution video with physics-aware motion, temporal consistency, and optional multi-character support. Compared to the standard version, Pro delivers higher fidelity output, broader resolution choices, and enhanced motion coherence for production-grade results.

• Need to animate an existing image? Try Sora 2 Image-to-Video Pro
• Looking for a lower-cost option? Try Sora 2 Text-to-Video

Why Choose This?

• Premium cinematic quality Higher fidelity output with enhanced detail, motion coherence, and richer scene composition than the standard version.

• Physics-aware motion Understands contact, inertia, and momentum so objects, people, and environments move and interact believably.

• Multi-character scene support Reference pre-defined character IDs to maintain consistent character identity across a single generation — no manual compositing required.

• Broad resolution support Six output sizes spanning portrait and landscape orientations from 720p up to 1080p-class resolutions, suitable for social, cinematic, and broadcast workflows.

• Temporal consistency Stable identities, minimal flicker and ghosting, and clean frame-to-frame transitions throughout.

• Scalable duration Generate clips from 4 seconds up to 20 seconds to match your pacing and production needs.

Parameters

How to Use

1.2. Select size — choose portrait or landscape orientation and resolution tier based on your delivery target. 3. Set duration — choose 4, 8, 12, 16, or 20 seconds based on your scene length. 4.5. Submit — generate, preview, and download your video.

Example Prompt

In a 90s documentary-style interview, an old Swedish man sits in a study and says, “I still remember when I was young.”

Pricing

Billing Rules

• 720×1280 / 1280×720: $0.30 per second
• 1024×1792 / 1792×1024: $0.50 per second
• 1080×1920 / 1920×1080: $0.70 per second
• Duration options: 4, 8, 12, 16, or 20 seconds
• Billing is based on the selected duration and size, not actual playback length

Best Use Cases

• Cinematic Storytelling — Render rich, narrative-driven scenes from detailed text descriptions.
• Commercial & Brand Video — Produce premium-quality footage for marketing campaigns without a film crew.
• Social Media Content — Generate portrait-format clips optimized for Reels, TikTok, and Shorts.
• Documentary & Interview Style — Recreate specific camera aesthetics and era-accurate visual styles.
• Multi-Character Scenes — Animate ensemble casts with consistent identity across the full clip.

Pro Tips

• The more specific your prompt, the better the result — include camera style, lighting, era, mood, and character behavior.
• Use portrait sizes (720×1280, 1024×1792, 1080×1920) for mobile-first platforms and landscape for cinematic or desktop formats.
• Start with a 4-second generation at a lower resolution to validate your prompt before committing to longer, higher-resolution runs.
• Character IDs must be created in advance — ensure they are saved and accessible in your account before adding them.

Notes

• Character IDs reference existing character profiles — this model does not create new character definitions.
• Please follow OpenAI’s usage policies when crafting prompts.

Related Models

• Sora 2 Text-to-Video — Standard version at lower cost for faster iteration.
• Sora 2 Image-to-Video Pro — Animate a still image into a cinematic video with the same 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": "720*1280",
  "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/text-to-video-pro" \
  -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