How to Use the Sora 2 Text to Video API: text to video integration guide (2026)
Learn how to call the Sora 2 Text to Video API on NamiFusion: parameters, pricing (from ≈$0.400) and runnable copy-paste code — try it in the playground first.
Sora 2 Text to Video is a text to video model by OpenAI: SOTA Physics Simulation. Generates video with accurate physics, strong steerability, and fully synchronized audio. On NamiFusion you can try it in the playground (exact quote shown before you submit), then call it through one unified REST API — a typical run costs about $0.400.
TL;DR
· Task type: text to video, provided by OpenAI
· Pricing: about $0.400 per typical run ($1 = 100 credits), pay-as-you-go
· Getting started: playground (exact quote before submit) → create an API key → one POST request
· Tunable parameters: 3 (see the table below)
· No platform watermark; commercial use allowed (per the Terms of Service)
What can you build with Sora 2 Text to Video?
Short-form video and ad clips: go from a prompt or a single image to publishable motion content.
Product demos and concept previews: validate storyboards and visual direction cheaply before any shoot.
A social content factory: batch vertical clips and ride trending topics fast.
Remixing existing assets: image-to-video brings static work to life and extends its lifespan.
How do you call this API?
1. Sign up on NamiFusion and create a key on the API Keys page (free credits on signup).
2. Submit a task with the cURL example below, passing your key as a Bearer token.
3. Poll the task status with the returned task_uuid and read the output URLs when completed.
# 1) Submit — returns { "task_uuid": "..." }
curl -X POST "https://www.namifusion.com/api/v1/marketplace/run/openai/sora-2/text-to-video" \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"input": {
"prompt": "Cinematic, photorealistic wide shot of a vintage steam train smashing through a deep snowdrift in the mountains. Massive chunks of snow are displaced with realistic physics, creating a white cloud around the black locomotive. The camera pans to follow the train'\''s momentum. 8k resolution, highly detailed metal textures. Audio: Deafening steam whistle, rhythmic mechanical chugging, and the heavy impact of snow being crushed.",
"duration": "4",
"size": "720*1280"
}
}'
# 2) Poll until status is "completed", then read the output URLs
curl "https://www.namifusion.com/api/v1/marketplace/run/tasks/TASK_UUID" \
-H "Authorization: Bearer YOUR_API_KEY"What parameters does it take?
prompt (Prompt): required
duration (Duration): optional, default "4"
size (Resolution): optional, default "720*1280"
How do you write prompts for Sora 2 Text to Video?
1. Subject first: lead with the actor and action, then add environment, lighting and style ("an astronaut sprinting through a neon street in the rain, cinematic, shallow depth of field").
2. Concrete nouns beat stacked adjectives: "85mm portrait lens, golden-hour backlight" works far better than "very beautiful, ultra high quality".
3. Change one variable per iteration: pin the seed to reproduce a result, tweak a single phrase at a time so you know what actually moved the output.
4. State negatives positively: instead of "no blur", ask for "sharp focus, crisp details".
How much does it cost?
Pay-per-use in credits. A typical run costs about $0.400 ($1 = 100 credits); the exact price varies with parameters like resolution or duration, and the playground shows the exact quote before you submit.
Sora 2 Text to Video
State-of-the-Art Video Generation: Physics-Aware, Synchronized Audio, and High Steerability.
OpenAI Sora 2 (T2V) is the definitive model for generative video. Building on the foundational Sora architecture, Sora 2 introduces a massive leap in physics accuracy—understanding inertia, collision, and gravity naturally. It generates high-fidelity videos from text prompts with fully synchronized audio, sharp high-frequency details, and a vast stylistic range from photorealism to anime.
🚀 Key Features
- Physics-Aware Motion: The model learns real-world physics, simulating contact, inertia, and momentum so objects move, collide, and interact believably.
- Synchronized Audio: Generates native audio that aligns perfectly with visuals, including lip-syncing, beat-aware editing cuts, and action-matched ambience.
- Complex Scene Reasoning: Capably handles multiple subjects, occlusions, and depth perception even during long, complex camera maneuvers.
- Cinematic Camera Literacy: Simulates professional camera work—natural pans, smooth push-ins, and handheld aesthetics—without warping or "jelly" artifacts.
- High-Frequency Detail: Preserves fine textures like skin pores, fabric weaves, and foliage without the artificial "plastic" look common in AI video.
- Strong Steerability: Highly responsive to prompt engineering. Changes to duration, FPS, or motion strength yield predictable, controllable results.
🛠️ Technical Specifications
| Parameter | Details |
|---|---|
| Model | OpenAI Sora 2 T2V |
| Input | Text Prompt (Description + Style + Audio Cues) |
| Output | Video + Synchronized Audio |
| Durations | 4s, 8s, 12s |
| Styles | Photoreal, 3D, Anime, Illustrative, Documentary |
| Latency | Optimized (No cold starts) |
Key Parameters:
prompt: Describe the scene, artistic style, camera movement, and audio atmosphere.duration: Select 4, 8, or 12 seconds.
💰 Pricing
Linear Pricing Model: $0.10 per second.
| Duration | Total Cost |
|---|---|
| 4 Seconds | $0.40 |
| 8 Seconds | $0.80 |
| 12 Seconds | $1.20 |
FAQ
Can I try it for free first?+
Signup gives you free credits, but they currently apply only to selected in-app face-swap features — this model is pay-as-you-go. The playground still lets you try it without code, with the exact quote shown before you submit.
Can I use the output commercially? Is there a watermark?+
Yes, outputs are yours to use commercially, and NamiFusion adds no platform watermark — subject to the Terms of Service and applicable law.
What is the content policy?+
NamiFusion is an unfiltered engine: no arbitrary restrictions and NSFW-friendly, but illegal content and non-consensual use of real people are prohibited — see the Terms of Service.
How long does a Sora 2 Text to Video task take?+
It depends on parameters — images usually take seconds, videos tens of seconds to minutes. The API returns a task_uuid for polling.
What are the resolution and duration limits?+
See the parameter table above — each model lists its available resolution and duration options there and in the playground.