muapi Logomuapi Logo
muapi Logomuapi Logo

Seedance 2.5 Text to Video: AI Video Generator

Generate video from text with Seedance 2.5. Early-access build with 720p output, and 30-second clips. Try free — pay per generation.

Tutorial

📝

Overview

About this model

Seedance 2.5 Text-to-Video is the early-access build of ByteDance's next-generation Seedance model, generating cinematic video directly from a detailed text prompt. It supports clips up to 30 seconds — double the 15-second limit of Seedance 2.0 — at 720p output. A lower-cost 480p variant is also available for previews and drafts.

1Rapid prototyping: Generate a full-length 30-second draft from a prompt alone before committing to production.
2Social content: Produce short-form video clips for ads and social posts directly from a script.
3Concept visualization: Turn a scene description into a moving reference for storyboarding or previs.
4Marketing: Generate cinematic b-roll from text prompts without shooting footage.
💰

Pricing & Value

Cost analysis

muapiapp$0.60/sec (720p) or $0.30/sec (480p)

Pay-per-generation pricing with no subscription.

Fal.aiNot available

Seedance 2.5 is not listed on Fal.ai.

ReplicateNot available

Seedance 2.5 is not listed on Replicate.

* Competitor pricing is estimated based on similar model architectures and usage tiers.

⚙️

Technical Details

Configuration schema

Promptstring

Text prompt describing the video scene and motion.

Default ValueA cinematic tracking shot through a city park after rain, soft cloudy light, wet pavement reflections, smooth camera movement.
Durationint

The duration of the generated video in seconds.

Default Value5
Aspect RatioEnum (7 options)

Aspect ratio of the output video.

Default Value16:9
Seedint

Random seed for reproducible generation. Use -1 for random.

Default Value42
📖

Implementation Guide

Developer documentation

How to Use Seedance 2.5 Text-to-Video

  1. Write a Detailed Prompt

    • Include scene, lighting, camera movement, and motion specifics.
    • Example: "A cinematic tracking shot through a city park after rain, soft cloudy light, wet pavement reflections, smooth camera movement."

  2. Configure Output

    • Set duration from 4 to 30 seconds.
    • Choose aspect_ratio (16:9, 9:16, 1:1, 4:3, 3:4, 21:9, 9:21).
    • Optionally set seed for reproducible output.

  3. Submit via the API

curl -X POST https://api.muapi.ai/api/v1/seedance-2.5-text-to-video \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A cinematic tracking shot through a city park after rain, soft cloudy light, wet pavement reflections, smooth camera movement.",
    "duration": 5,
    "aspect_ratio": "16:9"
  }'
  1. Poll and Download
    • Poll GET /api/v1/predictions/{request_id}/result until status is completed, then retrieve the video URL from output.
❓

Common Questions

Frequently asked

What does Seedance 2.5 Text-to-Video do?

It generates video directly from a text prompt describing the scene, camera movement, and atmosphere, with no image or video reference required.

What resolution does it output?

720p by default. A cheaper 480p variant is available separately.

Does it support 1080p?

Not yet. This early-access build currently supports 480p and 720p; native 1080p support is planned for a future update.

How long can generated videos be?

Between 4 and 30 seconds, configurable via the `duration` parameter.

Can I reproduce the same output twice?

Yes — pass an explicit `seed` value (0 to 4294967295) to reproduce a generation, or use -1 for a random seed each time.

How is this different from Seedance 2.5 Image-to-Video?

Text-to-Video generates purely from a prompt. For animating a still image, use Seedance 2.5 Image-to-Video; for keyframe transitions or multi-reference blending, use the First & Last Frame or Omni Reference endpoints.