Seedance 2.5 Text To Video
Seedance 2.5 (Text-to-Video) generates native cinematic video up to 30 seconds directly from a prompt, with native audio-visual synchronization and stronger precision in editing and generation control than Seedance 2.0. Built on ByteDance's Seed architecture for production-ready creative workflows.
Key Features
- Native 30-second clips generated directly from text — no reference image required.
- Up to 50 full-modal reference assets — combine images, videos and audio to steer style, character and motion without leaving text-to-video mode.
- Native audio-visual synchronization — generates video with synchronized sound effects, dialogue and ambience in a single pass.
- Sharper editing and generation control than Seedance 2.0, courtesy of ByteDance's next-generation Seed architecture.
- Director-level control over camera movement, lighting, shadows and character performance.
- Strong instruction adherence — accurately renders complex multi-element, multi-scene scripts 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: 4-30 (default: 5). |
| resolution | No | Output resolution: 480p, 720p (default), or 1080p. |
| reference_images | No | Up to 50 reference image URLs for style/subject guidance. |
| reference_videos | No | Reference video URLs (each 1.8-30.2s) for motion guidance. |
| reference_audios | No | Reference audio URLs for audio style guidance. |
| bitrate_mode | No | Bitrate quality: standard (default) or high. |
| 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 30 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-2.5/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 | $0.76 |
| 480p | 5s | $0.95 |
| 480p | 6s | $1.14 |
| 480p | 8s | $1.52 |
| 480p | 10s | $1.90 |
| 480p | 12s | $2.28 |
| 480p | 15s | $2.85 |
| 480p | 20s | $3.80 |
| 480p | 25s | $4.75 |
| 480p | 30s | $5.70 |
| 720p | 4s | $1.76 |
| 720p | 5s | $2.20 |
| 720p | 6s | $2.64 |
| 720p | 8s | $3.52 |
| 720p | 10s | $4.40 |
| 720p | 12s | $5.28 |
| 720p | 15s | $6.60 |
| 720p | 20s | $8.80 |
| 720p | 25s | $11.00 |
| 720p | 30s | $13.20 |
| 1080p | 4s | $4.20 |
| 1080p | 5s | $5.25 |
| 1080p | 6s | $6.30 |
| 1080p | 8s | $8.40 |
| 1080p | 10s | $10.50 |
| 1080p | 12s | $12.60 |
| 1080p | 15s | $15.75 |
| 1080p | 20s | $21.00 |
| 1080p | 25s | $26.25 |
| 1080p | 30s | $31.50 |
Billing rules
- 480p / 4s: $0.76.
- 720p / 4s: $1.76.
- 1080p / 4s: $4.20.
- Longer durations scale proportionally.
- Failed generations are not charged.
Best Use Cases
- Film production — generate longer cinematic footage from screenplays and treatments.
- Commercials — create professional, multi-beat 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 longer 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 the extended 30-second ceiling and up to 50 reference assets for multi-scene narratives.
- Start with 5s at 480p for fast iterations, then render final at 1080p.
Notes
- Audio is generated natively by default — no need for separate audio tools.
- Duration range: 4-30 seconds (continuous selection).
- Supports up to 50 combined reference images, videos, and audio clips.
- Successor to Seedance 2.0 with a longer duration ceiling and richer reference support.