Sora 2 API
Access OpenAI's flagship multimodal model. Generate physically accurate video with perfectly synchronized dialogue and SFX through the unified Sora 2 API on EvoLink.
A serene mountain landscape at golden hour, with mist rolling through the valleys and sunlight breaking through the clouds. The camera slowly pans across the scene, revealing distant peaks and a winding river below.
Upload reference images for video generation
Click to upload or drag and drop
Supported formats: JPG, JPEG, PNG, WEBP
Maximum file size: 10MB; Maximum files: 10
Pricing
Sora 2 API — OpenAI’s audio-visual engine
Create 10–15s cinematic shots where sound matches motion. Leverage the Sora 2 API for superior physics, multi-shot consistency, and granular camera control.

What can you build with the Sora 2 API?
Synchronized audiovisual generation
The Sora 2 API renders video and audio in a single pass. Eliminate external Foley work with lip-synced dialogue, reactive sound effects, and adaptive scores.
Start Using Sora 2 API
High-fidelity physics simulation
Reduce hallucinations with a world model that understands gravity and collision. The Sora 2 API delivers usable footage that respects real-world object interactions.
Start Using Sora 2 API
Director-level camera control
Stop gambling on random seeds. Pass precise camera parameters via the Sora 2 API to define lens curvature, dolly zooms, and distinct visual styles.
Start Using Sora 2 API
Why developers choose the Sora 2 API
Engineering teams and agencies switch to the Sora 2 API to cut production pipelines in half by generating sound and vision simultaneously.
Unified Audio-Visual Pipeline
Generating audio alongside video via the Sora 2 API removes the need for separate TTS or audio-stitching microservices.
Commercial-Grade Consistency
Sora 2 significantly lowers rejection rates by adhering to strict physics rules, ensuring assets are ready for production use.
Zero-Friction Scalability
Scale from prototyping in the playground to millions of API requests on EvoLink without managing GPU infrastructure.
How to integrate the Sora 2 API
Generate your first audiovisual clip in under three minutes using EvoLink’s standardized SDKs.
Step 1 · Authenticate & Prompt
Initialize the client with your EvoLink key. Send a text prompt or reference image to the `sora-2` endpoint to define your scene.
Step 2 · Configure Parameters
Set `audio_enabled=true`, define aspect ratios (16:9, 9:16), and specify camera motion vectors within your API request body.
Step 3 · Retrieve & Deploy
Poll the webhook for completion. Receive a generated MP4 with embedded audio, ready for streaming or editing workflows.
Sora 2 API Capabilities
Technical highlights from the September 2025 model release
Integrated Audio Synthesis
The API generates 48kHz audio synced to video actions (e.g., footsteps, explosions) automatically.
Advanced Physics Engine
Model understands mass and velocity, preventing objects from merging or floating unnaturally.
Temporal Coherence
Maintain character identity and background consistency across multiple generated clips.
Granular Camera API
Developers can pass JSON objects defining pan, tilt, zoom, and focal length values.
Ethical Cameo System
Securely insert authorized character likenesses using the API's consent-verification layer.
C2PA Watermarking
All Sora 2 API outputs include invisible cryptographic metadata for trust and safety compliance.
Compare Sora 2 API vs Competitors
Select the best model for your automated video workflow
| Model | Duration | Resolution | Price | Strength |
|---|---|---|---|---|
| Sora 2 API | 10–15s (Standard) | Up to 1080p | ~$0.10–0.50 / clip | Native audio sync, superior physics simulation, reliable API uptime. |
| VEO3 Fast | 8s | 720p / 1080p | ~$0.36 / clip (via EvoLink) | Rapid generation speed, deep integration with Google ecosystem. |
| Runway Gen-3 | 5–10s | 720p (Upscale avail) | Credit system (varies) | Excellent creative style controls, fast iteration for shorter clips. |
Sora 2 API - Frequently Asked Questions
API Reference
Select endpoint
Authentication
All APIs require Bearer Token authentication.
Authorization:
Bearer YOUR_API_KEY/v1/videos/generationsCreate Video
Sora 2 (sora-2) model supports text-to-video, image-to-video and other modes.
Asynchronous processing mode, use the returned task ID to .
Generated video links are valid for 24 hours, please save them promptly.
Important Notes
- Currently Sora2's content moderation mechanism is very strict, tasks may fail due to this.
- Image input containing real human figures is not currently supported.
Request Parameters
modelstringRequiredDefault: sora-2Video generation model name.
sora-2promptstringRequiredPrompt describing what kind of video to generate.
Notes & Constraints
- Limited to 5000 tokens
A cat playing pianoaspect_ratiostringOptionalDefault: 9:16Video aspect ratio, `16:9` generates landscape video, `9:16` generates portrait video.
| Value | Description |
|---|---|
| 16:9 | Landscape video |
| 9:16 | Portrait video |
'16:9'image_urlsarrayOptionalReference image URL list for image-to-video feature.
Notes & Constraints
- Images containing real human figures are not supported
- Max 1 image per request
- Max size: 10MB
- Formats: .jpg, .jpeg, .png, .webp
- URLs must be directly viewable by the server
http://example.com/image1.jpgremove_watermarkbooleanOptionalDefault: trueWhether to remove video watermark.
| Value | Description |
|---|---|
| true | Remove watermark. Higher pricing. |
| false | Keep watermark. Standard pricing. |
truedurationintegerOptionalDefault: 10Specifies the generated video duration in seconds.
| Value | Description |
|---|---|
| 10 | 10 seconds duration |
| 15 | 15 seconds duration (Higher Cost) |
Notes & Constraints
- Billing is based on duration
10callback_urlstringOptionalHTTPS callback address after task completion.
Notes & Constraints
- Triggered on completion, failure, or cancellation
- Sent after billing confirmation
- HTTPS only, no internal IPs
- Max length: 2048 chars
- Timeout: 10s, Max 3 retries
https://your-domain.com/webhooks/video-task-completed