Seedance 2.5 Text-to-Video API

Overview

Seedance 2.5 Text-to-Video is the text-to-video interface of ByteDance's Seedance 2.5 model on iCreat: input a text prompt to generate video clips with natively synchronized audio. The full model supports up to 50 multimodal reference inputs; the current iCreat interface is driven by text prompts. Developers invoke bytedance/seedance-2-5/text-to-video through an asynchronous task queue, with 480p / 720p output and 4-30 second durations.

bytedance/seedance-2-5/text-to-video

Core Capabilities

Text-to-video generation. A text prompt alone drives video generation with no reference materials required—ideal for turning copy, scripts, and creative descriptions into video quickly.

30-second one-take generation. A full narrative arc—setup, progression, turning point, payoff—fits in a single render without post-stitching.

Native synchronized audio. Dialogue, sound effects, and music are generated together with the picture in one pass (generate_audio: true).

Multilingual prompts. Supports Chinese, English, Japanese, Indonesian, Spanish, and Portuguese.

Asynchronous task design. Submit → poll → retrieve workflow that is batch-friendly and easy to integrate with fault tolerance.

Review mechanism. need_review submits assets containing faces or copyrighted IP for official review to avoid generation failure.

Model Comparison

Seedance 2.5 Text-to-Video (iCreat) vs Seedance 2.5 (Full Model)

Seedance 2.5 Text-to-Video vs Gemini Omni Flash vs Kling V3 Omni

Input

Text prompt is required. Reference images are optional and passed through the multimodal content array.

Reference image requirements (if used):

• Formats: jpeg、png、webp、bmp、tiff、gif、heic、heif
• Aspect ratio (w/h): 0.4–2.5
• Width and height: 300–6000 px
• Max 30 MB per image; max 64 MB request body

Parameters

Chinese prompts must not exceed 2000 characters; English prompts must not exceed 2000 words. Overly long prompts may dilute key information and cause the model to ignore details.

Pricing

Total cost = unit price × output video duration

Quick Start

Get your API Key from https://icreat.ai/hub/keys.

Submit a text-to-video task:

curl --fail-with-body --connect-timeout 10 --max-time 60 \
  -X POST https://api.icreat.ai/v1/task/submit/bytedance/seedance-2-5/text-to-video \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "content": [
    {
      "type": "text",
      "text": "A cat is playing with a ball"
    }
  ],
  "generate_audio": true,
  "ratio": "3:4",
  "duration": 5,
  "resolution": "480p"
}'

The server returns:

{ "task_id": "task-xxx" }

Poll task status:

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/query-status" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "task_id": "task-xxx"
}'

When the status is SUCCEEDED, fetch the result:

curl --connect-timeout 10 --max-time 60 \
  -X POST "https://api.icreat.ai/v1/task/get-result" \
  -H "Authorization: Bearer ${ICREAT_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
  "task_id": "task-xxx"
}'

Output

submit → task_id → query-status → get-result

After submitting, poll query-status with the task_id until the status is SUCCEEDED, then call get-result with the same task_id to retrieve the generated video.

Use Cases

Copy and script to video. Turn ad copy, short-video scripts, and creative descriptions directly into video with synchronized audio—suited to content creation and marketing.

Brand films and ads. A 30-second spot is one render; describe the product and brand tone in text so the look holds from the first frame to the last.

Story shorts and drama. Describe plot, characters, and camera moves in text to quickly generate multi-scene narrative clips.

Dialogue-led scenes. Quoted spoken lines and described sound design keep performance, timing, and effects aligned.

Limitations

The current iCreat interface is driven by text prompts; video and audio reference inputs are not exposed (the full model supports up to 50 multimodal inputs).

Chinese prompts must not exceed 2000 characters; English prompts must not exceed 2000 words. Overly long prompts may dilute key information.

If reference images containing faces or copyrighted IP are used, need_review: true is required; otherwise generation may fail.

API output resolution is capped at 480p / 720p.

FAQ

How do I get an API Key?

Create one at https://icreat.ai/hub/keys and pass it via the Authorization: Bearer header.

Do I need to provide a reference image for Text-to-Video?

No. A text prompt alone drives generation; reference images are optional for extra control over the visual content.

What does duration: -1 mean?

It lets the model choose the video length automatically instead of a fixed 4-30 second value.

What does ratio: adaptive do?

The model automatically selects the aspect ratio based on the input content.

480p or 720p?

Use 480p for fast, low-cost iteration and 720p when more detail is required.

What is the difference between the Text-to-Video interface and the full Seedance 2.5 model?

iCreat currently drives generation with text prompts (Text-to-Video); the full model also supports video references, audio references, timestamp-level editing, and video extension.