Seedance · Text to video

Seedance 2.5

Seedance 2.5 elabora un'intera ripresa in una volta sola: clip coerenti a ripresa unica fino a 30 secondi con audio sincronizzato.

Best for

Riprese lunghe a singola inquadratura

Coerenza dell'intera ripresa

Audio nativo

da 106 crediti Manifold

Generator controls

Describe the shot

DurationAspect ratioResolutionSeed

Generate audio

Output

Your generated shot will appear here, ready to download or place on the Studio timeline.

API request

curl https://manifoldgen.com/api/service \
  -X POST \
  -H "Authorization: Bearer $MANIFOLDGEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "service": "video_generate",
  "model": "seedance-2.5-text-to-video",
  "prompt": "A cinematic tracking shot through a rain-soaked night market, natural motion, rich reflections",
  "duration": 4,
  "aspect_ratio": "16:9",
  "resolution": "480p",
  "output_format": "mp4",
  "include_audio": true
}'

The API and this tester use the same request. Provider routing stays behind ManifoldGen.

How to use Seedance 2.5

How to Use Seedance 2.5 — prompting patterns, tier choice, and troubleshooting.

Read the guide

Build this workflow into your product

Stable JSON API, async jobs, durable outputs, and the same ManifoldGen billing.

API reference