Skip to main content
Core.Today
|
ByteDanceMediumUltra

Seedance 2.5 Text to Video

ByteDance Seedance 2.5 text-to-video via Fal.AI. Generates a native single-shot clip of up to 30 seconds at 480p/720p from a text prompt alone, reasoning about the whole shot at once so motion, lighting, and subject identity stay coherent from first frame to last. Synchronized audio (dialogue, sound effects, music) is generated in the same pass.

4920 credits
per 5s 720p video โ€” billed per second (480p 513/s, 720p 1100/s)
Native single-shot generation up to 30 seconds โ€” no clip stitching
Synchronized audio generated with the video, including lip-synced speech
480p and 720p output tiers, priced per second
Seven aspect ratios from 21:9 ultrawide to 9:16 vertical, or auto
Multilingual prompts

Run it right now

Test this model instantly in the Console Playground โ€” no code required

Sign in to try

Use with AI Assistant

Copy usage instructions for Claude, ChatGPT, or other AI

Quick Start

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "bytedance/seedance-2.5/text-to-video",
  "input": {
    "prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
    "duration": "5",
    "resolution": "720p",
    "aspect_ratio": "auto",
    "generate_audio": true
  }
}'

Parameters

ParameterTypeRequiredDefaultDescription
promptstringYes-The text prompt used to generate the video. For dialogue, put the spoken words in double quotes โ€” the model generates matching lip movements and voice.
durationstringYes5Duration of the video in seconds (4-30), sent as a string. Required โ€” upstream also accepts "auto", but the resulting length is unknown at request time and cannot be billed accurately, so this gateway requires an explicit duration.
456789101112131415161718192021222324252627282930
resolutionstringNo720pVideo resolution โ€” 480p for faster generation, 720p for balance.
480p720p
aspect_ratiostringNoautoThe aspect ratio of the generated video. Use 16:9 for landscape, 9:16 for portrait/vertical, 1:1 for square, 21:9 for ultrawide cinematic, or auto to let the model decide.
auto21:916:94:31:13:49:16
generate_audiobooleanNotrueWhether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated.

Common Parameters

Common parameters used when calling POST /v1/predictions.

ParameterTypeRequiredDefaultDescription
modelstringYes-Model identifier
inputobjectYes-Object containing the model-specific parameters from the table above
output_folderstringNo-Folder path for output files (max 256 chars, '..' not allowed)
webhook_urlstringNo-Webhook URL to call on completion
is_publicbooleanNofalseIf true, output files are also available via permanent public URLs

Examples

Multi-scene prompt in one take

A single prompt describing a scene change; the model keeps subjects and style consistent across the cut.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "bytedance/seedance-2.5/text-to-video",
  "input": {
    "prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
    "duration": "5",
    "resolution": "720p",
    "aspect_ratio": "auto",
    "generate_audio": true
  }
}'

Vertical 480p draft

Explore composition cheaply at 480p in a 9:16 frame before rendering the 720p master.

curl -X POST "https://api.core.today/v1/predictions" \
  -H "Content-Type: application/json" \
  -H "X-API-Key: cdt_your_api_key" \
  -d '{
  "model": "bytedance/seedance-2.5/text-to-video",
  "input": {
    "prompt": "A barista pours latte art in a sunlit cafe, close-up on the cup, warm morning light, gentle jazz in the background.",
    "duration": "6",
    "resolution": "480p",
    "aspect_ratio": "9:16",
    "generate_audio": true
  }
}'

Tips & Best Practices

1duration is a string on this endpoint โ€” send "5", not 5. Integers are rejected before the request reaches the provider.
2Billing is per second of output, so a 30-second take costs six times a 5-second one. Iterate short, finish long.
3Draft at 480p (roughly half the per-second rate) and re-render the keeper at 720p.
4Put dialogue in double quotes inside the prompt to get lip-synced speech instead of narration-style audio.

Use Cases

Long-form single-take social clips that would otherwise need multi-shot stitching
Narrated product or explainer videos where speech must match on-screen lip movement
Concept and mood films generated straight from a written treatment
Rapid 480p style exploration before committing to a 720p final render