Seedance 2.0 Mini Text-to-Video API

seedance-2.0-mini/text-to-video

Seedance 2.0 Mini Text-to-Video API turns a text prompt into a 4–15 second video at 480p or 720p. A request can set one of seven aspect ratios and include generate_audio, return_last_frame, web_search, and seed; image, video, and audio inputs are not accepted.

Input

Prompt

0/20000

Resolution

Duration

Aspect ratio

Generate audio

Ask the model to generate an audio track with the video.

Advanced

Return last frame

Keep the video result and request the final frame as an additional file.

Web search

Send the optional web_search Boolean field.

Seed

Output

Idle

Your generated files will appear here

Set the inputs, choose a duration, then run the asynchronous video task.

Continue with

Seedance 2.0 Mini Image-to-Video Seedance 2.0 Mini Reference-to-Video

Examples

One continuous four-second shot in a rain-wet night market. A fictional adult courier in an amber raincoat starts a small unbranded red delivery scooter beside a steaming noodle stall and pulls away. The camera tracks low beside the rear wheel from a medium-wide view to a medium view. Keep the courier, raincoat, scooter, stall, and camera direction consistent. Use believable acceleration, restrained tire spray, wet neon reflections, and natural cloth motion. Synchronized audio: one engine start, light rain on the awning, tire hiss on wet pavement, and quiet cooking sizzle. No cuts, no extra people entering frame, no dialogue, no readable text, no logos, no products, no advertising, no watermark.

REST API

Quick Start

Authenticate, submit the smallest useful text request, then retrieve the asynchronous video result.

Connect to the Vidgo API

Create an API key, keep it on your server, and send it as a Bearer token.

Endpoint: POSThttps://api.vidgo.ai/api/generate/submit
Authentication: Authorization: Bearer VIDGO_API_KEY

Submit one generation task

Send the model ID and required input fields. A successful response returns a task_id immediately.

Submit request

curl --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "seedance-2.0-mini/text-to-video",
  "input": {
    "prompt": "One continuous four-second shot in a rain-wet night market. A fictional adult courier in an amber raincoat starts a small unbranded red delivery scooter beside a steaming noodle stall and pulls away. The camera tracks low beside the rear wheel from a medium-wide view to a medium view. Keep the courier, raincoat, scooter, stall, and camera direction consistent. Use believable acceleration, restrained tire spray, wet neon reflections, and natural cloth motion. Synchronized audio: one engine start, light rain on the awning, tire hiss on wet pavement, and quiet cooking sizzle. No cuts, no extra people entering frame, no dialogue, no readable text, no logos, no products, no advertising, no watermark.",
    "duration": 4,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "return_last_frame": true,
    "seed": 24082401
  }
}'

Wait for the result

Poll only for not_started or running, or provide callback_url and handle the flat terminal callback body.

Track status

GET https://api.vidgo.ai/api/generate/status/5I2XP283UB2BTW3R

Start near a 2–5 second interval and back off for long jobs. Stop on finished or failed. Network timeouts are transport errors; a failed task is a terminal business result. callback_url receives a flat terminal task object.

not_startedrunningfinishedfailed

Submit response

{
  "code": 200,
  "data": {
    "task_id": "5I2XP283UB2BTW3R",
    "status": "running",
    "created_time": "2026-08-24T08:50:43"
  }
}

Finished response

{
  "code": 200,
  "data": {
    "task_id": "5I2XP283UB2BTW3R",
    "status": "finished",
    "created_time": "2026-08-24T08:50:43",
    "progress": 100,
    "error_message": null,
    "files": [
      {
        "file_type": "video",
        "file_url": "https://cdn.vidgo.ai/apis/models/bytedance/seedance-2.0-mini/text-to-video/v1/output.mp4"
      }
    ]
  }
}

Complete runnable example

This script combines submission, polling, terminal-state handling, timeout behavior, and result extraction.

Complete runnable example

set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"

REQUEST_BODY=$(cat <<'JSON'
{
  "model": "seedance-2.0-mini/text-to-video",
  "input": {
    "prompt": "One continuous four-second shot in a rain-wet night market. A fictional adult courier in an amber raincoat starts a small unbranded red delivery scooter beside a steaming noodle stall and pulls away. The camera tracks low beside the rear wheel from a medium-wide view to a medium view. Keep the courier, raincoat, scooter, stall, and camera direction consistent. Use believable acceleration, restrained tire spray, wet neon reflections, and natural cloth motion. Synchronized audio: one engine start, light rain on the awning, tire hiss on wet pavement, and quiet cooking sizzle. No cuts, no extra people entering frame, no dialogue, no readable text, no logos, no products, no advertising, no watermark.",
    "duration": 4,
    "resolution": "720p",
    "aspect_ratio": "16:9",
    "generate_audio": true,
    "return_last_frame": true,
    "seed": 24082401
  }
}
JSON
)

SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --request POST \
  --url "https://api.vidgo.ai/api/generate/submit" \
  --header "Authorization: Bearer $VIDGO_API_KEY" \
  --header "Content-Type: application/json" \
  --data "$REQUEST_BODY")

TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
if [ -z "$TASK_ID" ]; then
  printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
  exit 1
fi

while true; do
  STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
    --url "https://api.vidgo.ai/api/generate/status/5I2XP283UB2BTW3R" \
    --header "Authorization: Bearer $VIDGO_API_KEY")
  STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')

  case "$STATUS" in
    finished)
      printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
      break
      ;;
    failed)
      printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
      exit 1
      ;;
    not_started|running)
      sleep 2
      ;;
    *)
      printf 'Unexpected task status: %s
' "$STATUS" >&2
      exit 1
      ;;
  esac
done

Request Parameters

Send model and optional callback_url at the top level; put only the listed generation fields inside input. Media fields are rejected.

Field	Type	Required	Default	Description
model	string	Yes	—	Must be seedance-2.0-mini/text-to-video.
callback_url	string (URL)	No	—	Public callback endpoint for the terminal task result.
input	object	Yes	—	Container for model-specific fields.
input.prompt	string	Yes	—	Trimmed length 1–20,000.
input.duration	integer	Yes	—	Inclusive range 4–15; booleans and decimals are invalid.
input.resolution	string	No	720p	480p or 720p.
input.aspect_ratio	string	No	—	auto, 21:9, 16:9, 4:3, 1:1, 3:4, or 9:16.
input.generate_audio	boolean	No	—	Request generated audio.
input.return_last_frame	boolean	No	—	Request an additional final-frame file.
input.web_search	boolean	No	—	Optional Boolean field.
input.seed	integer	No	—	Optional integer with no published range.

Response Fields

Submission returns task identity. Status responses add progress, files, watermark URLs, or a failure message.

Field	Type	Description
code	integer	Business result code; successful responses use 0 or 200.
message	string	Human-readable response or error message when present.
data.task_id	string	Identifier used in the status path.
data.status	string	not_started, running, finished, or failed.
data.created_time	string	Task creation timestamp.
data.progress	integer	Reported completion percentage.
data.files[]	array	All successful output files.
data.files[].file_url	string	Direct result URL.
data.files[].file_type	string	Media type such as video or image.
data.files[].watermark_url	string \| null	Watermarked URL when available.
data.error_message	string \| null	Failure detail for failed tasks.

Task Lifecycle

Only not_started and running are pollable. finished and failed are terminal.

not_started
Accepted and waiting to begin.
running
Generation is active; continue polling with backoff.
finished
Successful terminal state; read every returned file.
failed
Failed terminal state; read error_message and stop.

Polling and Errors

Authentication401 means the Bearer key is missing or invalid; correct it before retrying.
Validation400 means the payload violates the contract; fix the named field.
Polling intervalStart around 2–5 seconds and increase the delay for long jobs or 5xx/429 responses.
Terminal statesStop immediately on finished or failed, and enforce a client timeout.
Callback optionProvide top-level callback_url for the final flat task object; polling remains available.

Model Specifications

Specification	Value	Details
Input mode	Text	Prompt only; media fields are rejected.
Output	Video + optional last frame	An asynchronous task may return multiple files.
Resolution	480p / 720p	720p is the API default.
Duration	4–15 seconds	Every integer in the inclusive range is accepted.
Aspect ratio	Auto + 6 fixed	Seven accepted composition values.
Billing basis	10 or 24 credits/s	Output seconds at the selected resolution.

View Seedance 2.0 Mini Text-to-Video API documentation

Seedance 2.0 Mini Text-to-Video

Seedance 2.0 Mini Text-to-Video API requires a text prompt and no source media. The prompt can name the subject, setting, action, camera, lighting, and sound; the asynchronous task returns files through status polling or callback_url.

Why use Seedance 2.0 Mini Text-to-Video API?

Submit only a text prompt.Use prompt to describe the subject, setting, action, camera, lighting, and sound without uploading source media.
Choose an integer duration from 4–15 seconds.duration accepts every integer from 4 through 15, including both limits.
Choose from seven aspect ratios.aspect_ratio accepts auto, 16:9, 9:16, 1:1, 21:9, 4:3, and 3:4.
Request audio and a final-frame file.generate_audio requests an audio track; return_last_frame requests an additional final-frame file.

Parameters

Parameter	Requirement	Description
prompt	Required	Trimmed scene description from 1 through 20,000 characters.
duration	Required	Integer output duration from 4 through 15 seconds; the Playground starts at 5 seconds.
resolution	Optional	Output resolution. The API defaults to 720p and the Playground also starts at 720p. Default`720p480p`
aspect_ratio	Optional	Auto or one of six fixed output ratios; the Playground starts at Auto. `auto16:99:161:121:94:33:4`
generate_audio	Optional	Boolean audio-generation request. The Playground sends true by default; the API has no declared default.
return_last_frame	Optional	Boolean request for an additional final-frame result. The Playground omits it until enabled.
web_search	Optional	Boolean field. The Playground omits web_search until enabled.
seed	Optional	Integer seed with no public minimum or maximum. Empty Playground values are omitted.

How to Use

Define the subjectName the subject, setting, and details that must stay visible.
Direct the actionDescribe one subject action, how the action begins, and where the action ends.
Set the cameraSeparate subject motion from shot size and camera movement.
Add light, mood, and soundSpecify lighting, atmosphere, and intended audio cues before submission.
Submit and trackRun the request, then poll the task ID or receive the terminal callback.

Pricing

Text-to-Video is billed only by output duration and resolution. One credit equals $0.005; optional audio, last frame, web search, and seed do not change the current rate.

Usage	Rate	Details
480p output	10 credits / output second	$0.050/s. A 5 second output uses 50 credits ($0.250).
720p output	24 credits / output second	$0.120/s. A 5 second output uses 120 credits ($0.600).

Best Use Cases

Storyboard previewsTurn a written shot into a 4–15 second video for checking action, camera direction, and framing before production.
Social variantsGenerate the same idea in landscape, square, portrait, or vertical compositions.
Camera-direction comparisonsSubmit separate prompts for locked, tracking, pushing, or orbiting camera movement and compare the returned videos.
Video drafts with audioName dialogue, sound effects, or ambience in prompt and set generate_audio to true.

Pro Tips

Write in this order: subject and setting, action, camera, lighting, mood, then sound.
Use concrete motion verbs and keep subject movement separate from camera movement.
Give short clips one main action instead of several competing events.
Describe the opening, development, and final beat when timing matters.
Choose the delivery ratio before describing framing and empty space.

Notes

Seedance 2.0 Mini Text-to-Video API does not accept image, video, audio, or reference-media fields.
Duration is required even though the Playground supplies a 5 second starting value.
The API defaults resolution to 720p; other Playground starting values are not API defaults.
Tasks are asynchronous. Poll only while status is not_started or running.

Related Models

Gemini Omni 1.1 Flash Text-to-Video preview

Gemini Omni 1.1 Flash Text-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Image-to-Video preview

Gemini Omni 1.1 Flash Image-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Reference-to-Video preview

Gemini Omni 1.1 Flash Reference-to-VideoGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

Gemini Omni 1.1 Flash Video Edit preview

Gemini Omni 1.1 Flash Video EditGoogle Gemini Omni 1.1 Flash video model with native audio, text-to-video, first/last-frame image-to-video, reference-image video, and 3–10 second video edit at 360p to 4K.

MiniMax H3 Max Turbo Text to Video preview

MiniMax H3 Max Turbo Text to VideoMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.

MiniMax H3 Max Turbo Image to Video preview

MiniMax H3 Max Turbo Image to VideoMiniMax H3 Max Turbo Text to Video turns text into coherent 5–15 second videos with synchronized native stereo audio and fast generation. It follows physical motion while rendering subtle changes in light and shadow.

MiniMax H3 Max Text to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

MiniMax H3 Max Image to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

MiniMax H3 Max Reference to Video preview

MiniMax H3 Max Reference to VideoMiniMax H3 Max Text to Video turns text prompts into cinematic video with native stereo audio, faster-than-real-time generation, and precise instruction following. It renders complex camera work and physical motion with fine detail across multiple resolutions and common aspect ratios.

Wan 3.0 Prime Text-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Image-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Prime Reference-to-Video preview

Wan 3.0 Prime Reference-to-VideoAlibaba Wan 3.0 Prime video model with text-to-video, image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds with optional synchronized audio.

Wan 3.0 Text-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Image-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

Wan 3.0 Reference-to-VideoAlibaba Tongyi Lab's Wan 3.0 multimodal video model with separate text-to-video, first/last-frame image-to-video, and reference-to-video workflows at 480p, 720p, or 1080p for 2 to 30 seconds.

FLUX 3 Text to VideoBlack Forest Labs FLUX 3 video model with text-to-video, image-to-video, first-last-frame, extend-video, and keyframes workflows at 720p or 1080p for 5 to 20 seconds, with optional native audio.

Seedance 2.0 Mini Text-to-Video API — Frequently asked questions

What is Seedance 2.0 Mini Text-to-Video API?

Seedance 2.0 Mini Text-to-Video API turns a text prompt into video. A successful submission returns task_id; after completion, data.files contains the video and can include a final-frame image when return_last_frame is true and the service returns that file.

How do I call Seedance 2.0 Mini Text-to-Video API?

Send POST /api/generate/submit with Authorization: Bearer VIDGO_API_KEY, set model to seedance-2.0-mini/text-to-video, and place prompt, duration, and other generation fields inside input. Poll the returned task_id or provide callback_url.

How is Seedance 2.0 Mini Text-to-Video API billed?

480p uses 10 credits ($0.050) per output second and 720p uses 24 credits ($0.120) per output second. The Run button displays both credits and the USD reference amount for the current request.

What inputs does Seedance 2.0 Mini Text-to-Video API accept?

prompt accepts 1–20,000 characters after trimming, duration accepts an integer from 4–15, resolution accepts 480p or 720p, and aspect_ratio accepts seven values. Optional fields include generate_audio, return_last_frame, web_search, and an integer seed.

How do I retrieve a Seedance 2.0 Mini Text-to-Video API result?

Poll GET /api/generate/status/{task_id} only while status is not_started or running. Stop on finished or failed; successful file URLs are in data.files[].file_url.

How should I choose among the three Seedance 2.0 Mini APIs?

Use Seedance 2.0 Mini Text-to-Video API without source media, Seedance 2.0 Mini Image-to-Video API for a required start frame and optional end frame, or Seedance 2.0 Mini Reference-to-Video API for image, video, or audio references.