Seedance 2.0 Fast Text To Video
Seedance 2.0 Fast (Text-to-Video) generates cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability — optimized for faster generation at lower cost. Built on Seed's unified multimodal architecture.
Key Features
- Generate video directly from text prompts — no source image required.
- Cinematic quality — produce smooth, coherent video with consistent subjects and scenes.
- Flexible creative control — specify camera angles, lighting, subject actions and mood.
- Multiple duration and resolution options for preview through production workflows.
- Coherent storytelling — maintains narrative consistency across the generated frames.
- Diverse styles — photorealistic, animated, stylized, or abstract visual outputs.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Detailed text description of the video scene to generate. |
| duration | No | Video length in seconds (default varies by model). |
| aspect_ratio | No | Output ratio: 16:9, 9:16, 4:3, 1:1 (default: 16:9). |
| resolution | No | Output resolution: 480p, 720p (default: 720p). |
How to Use
- Write a detailed prompt describing your video scene — include subject, action, setting, lighting and camera movement.
- Select aspect ratio and resolution appropriate for your use case.
- Set the desired duration for your video clip.
- Generate and download your video — iterate on the prompt for better results.
Code Examples
import os
import requests
response = requests.post(
"https://aircube.ai/api/v3/seedance-2.0-fast/text-to-video",
headers={
"Authorization": "Bearer " + os.environ["AIRCUBE_API_KEY"],
"Content-Type": "application/json",
},
json={
"prompt": "Aerial shot of a coastal city at golden hour, camera slowly descending toward the waterfront",
"duration": 8,
"aspect_ratio": "16:9"
},
timeout=300,
)
data = response.json()
if data["success"]:
print("ID:", data["data"]["id"], "Status:", data["data"]["status"])
else:
print("Error:", data["error"]["message"])Pricing
| Resolution | Duration | Cost |
|---|---|---|
| 480p | 4s | $0.26 |
| 480p | 5s | $0.33 |
| 480p | 6s | $0.40 |
| 480p | 8s | $0.53 |
| 480p | 10s | $0.66 |
| 480p | 12s | $0.79 |
| 480p | 15s | $0.99 |
| 720p | 4s | $0.53 |
| 720p | 5s | $0.66 |
| 720p | 6s | $0.79 |
| 720p | 8s | $1.06 |
| 720p | 10s | $1.32 |
| 720p | 12s | $1.58 |
| 720p | 15s | $1.98 |
Billing rules
- 480p / 4s: $0.26.
- 720p / 4s: $0.53.
- Longer durations scale proportionally.
- Failed generations are not charged.
Best Use Cases
- Content creation — generate video clips for social media, ads and marketing campaigns.
- Storyboard visualization — bring written concepts to life as video previews.
- Music video production — create visual sequences from lyrical descriptions.
- Educational content — generate explainer or demonstration clips from descriptions.
- Game and film pre-visualization — prototype scenes before full production.
Pro Tips
- Write prompts like a film director — include specific camera angles (close-up, wide shot, tracking shot).
- Describe lighting conditions (golden hour, dramatic shadows, neon glow) for mood control.
- Keep the scene description focused — one clear action or sequence per generation works best.
- Include temporal cues (slowly, suddenly, gradually) to guide the pacing of motion.
- Start with 16:9 for cinematic content and 9:16 for social media verticals.
Notes
- Video output is typically MP4 format.
- Generation time scales with duration and resolution.
- Complex prompts with multiple subjects may require iteration to achieve desired results.