Seedance 2.0 Text To Video
Seedance 2.0 (Text-to-Video) generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization, director-level camera and lighting control, and exceptional motion stability. Built on Seed's unified multimodal architecture, it leads on instruction adherence, motion quality, and visual aesthetics.
Key Features
- Unified multimodal architecture — a single model handling text, image, audio and video for comprehensive creative flexibility.
- Native audio-visual synchronization — generates video with synchronized sound effects, dialogue and ambience in a single pass.
- Director-level control — granular control over camera movement, lighting, shadows and character performance.
- Production-grade cinematic quality with Hollywood-level visual coherence.
- Exceptional motion stability — industry-leading motion coherence with stable subjects and fluid transitions.
- Strong instruction adherence — accurately renders complex multi-element scenes from detailed prompts.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Detailed cinematic description of the scene to generate. |
| aspect_ratio | No | Output format: 16:9 (default), 9:16, 4:3, 3:4, 1:1, 21:9. |
| duration | No | Video length in seconds: 4-15 (default: 5). |
| resolution | No | Output resolution: 480p, 720p (default), 1080p, or 4k. |
| reference_images | No | Up to 9 reference image URLs for style/subject guidance. |
| reference_videos | No | Up to 3 reference video URLs (max 15s total) for motion guidance. |
| reference_audios | No | Up to 3 reference audio URLs for audio style guidance. |
| enable_web_search | No | Enable web search for enhanced prompt understanding. |
| generate_audio | No | Generate synchronized audio (default: true). |
How to Use
- Write a cinematic prompt — describe subject, action, camera movement, lighting and mood.
- Choose aspect ratio: 16:9 for widescreen, 9:16 for vertical, or others.
- Set duration from 4 to 15 seconds.
- Optionally add reference images, videos, or audio for style guidance.
- Generate and download your video with synchronized audio.
Code Examples
import os
import requests
response = requests.post(
"https://aircube.ai/api/v3/seedance-2.0/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, waves crashing against the pier",
"duration": 8,
"aspect_ratio": "16:9",
"resolution": "1080p",
"generate_audio": true
},
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 | $0.48 |
| 480p | 5s | $0.60 |
| 480p | 6s | $0.72 |
| 480p | 8s | $0.96 |
| 480p | 10s | $1.20 |
| 480p | 12s | $1.44 |
| 480p | 15s | $1.80 |
| 720p | 4s | $0.96 |
| 720p | 5s | $1.20 |
| 720p | 6s | $1.44 |
| 720p | 8s | $1.92 |
| 720p | 10s | $2.40 |
| 720p | 12s | $2.88 |
| 720p | 15s | $3.60 |
| 1080p | 4s | $2.40 |
| 1080p | 5s | $3.00 |
| 1080p | 6s | $3.60 |
| 1080p | 8s | $4.80 |
| 1080p | 10s | $6.00 |
| 1080p | 12s | $7.20 |
| 1080p | 15s | $9.00 |
| 4k | 4s | $4.80 |
| 4k | 5s | $6.00 |
| 4k | 6s | $7.20 |
| 4k | 8s | $9.60 |
| 4k | 10s | $12.00 |
| 4k | 12s | $14.40 |
| 4k | 15s | $18.00 |
Billing rules
- 480p / 4s: $0.48.
- 720p / 4s: $0.96.
- 1080p / 4s: $2.40.
- 4k / 4s: $4.80.
- Longer durations scale proportionally.
- Failed generations are not charged.
Best Use Cases
- Film production — generate cinematic footage from screenplays and treatments.
- Commercials — create professional ad content directly from creative briefs.
- Music videos — generate visual sequences from lyrical descriptions.
- Premium social media — produce high-quality short-form video content.
- Film visualization — prototype scenes and camera movements before production.
Pro Tips
- Write prompts like a screenplay — subject, action, setting, camera, lighting.
- Specify camera movements explicitly: 'slow dolly in', 'handheld tracking shot', 'aerial crane up'.
- Include temporal language: 'gradually', 'suddenly', 'the camera slowly reveals'.
- Use reference images (up to 9) for character and style consistency across clips.
- Start with 5s at 480p for fast iterations, then render final at 1080p or 4K.
Notes
- Audio is generated natively by default — no need for separate audio tools.
- Duration range: 4-15 seconds (continuous selection).
- Supports up to 9 reference images, 3 reference videos, and 3 reference audios.
- Median generation time: approximately 252 seconds.