Bytedance Seedance V1 Pro T2V 480p API Documentation

Bytedance Seedance V1 Pro T2V 480p API Documentation

Playground

Seedance v1 Pro is a text-to-video 480p model for coherent multi-shot outputs with stable motion and accurate prompt adherence. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

> Notice — Service Stability > > The Seedance 1.0 family is being retired or has already been retired by its original provider. Until it is fully removed, the service is unstable: generations may fall back to alternative models without notice, results can differ from what this model used to produce, and the service can be temporarily unavailable. > > If you need an equally capable, stable alternative, we recommend Seedance 2: bytedance/seedance-2.0/text-to-video.

/seedance-v1-pro-t2v-480p is a text-to-video generation model. It transforms written prompts into dynamic short-form videos with controllable aspect ratios, camera settings, and reproducible seeds. Designed for creators, it offers cinematic quality at affordable pricing.

Why it looks great

• Text-to-video fidelity: interprets prompts into coherent, cinematic video scenes.
• Dynamic motion range: Wide dynamic range supporting both subtle and large-scale movements.
• Physical realism & stability: Maintains physical realism and stability across motion sequences.
• Complex interactions: Handles complex action sequences and multi-agent interactions.

Limits and Performance

• Output resolution: 480p
• Duration options: 5 seconds or 10 seconds
• Processing speed: ~20–60 seconds wall time per clip (varies by prompt complexity and queue load)

Pricing

Billing Rules

• Minimum charge: 5 seconds
• Per-second rate = (price per 5 seconds) ÷ 5
• Billed duration = video length in seconds (rounded up), with a 5-second minimum
• Total cost = billed duration × per-second rate (by output resolution)

How to Use

1. Write a prompt describing the scene, subject, and motion.
2. Select aspect_ratio: like 16:9, 9:16, or 1:1.
3. Choose duration (5s or 10s).
4. (Optional) Enable camera_fixed for a locked viewpoint.
5. (Optional) Set a seed for reproducibility.
6. Submit the job and download your generated video.

Pro tips for best quality

• Use detailed prompts with cinematic language (lighting, angles, dynamics).
• Pick aspect ratio according to publishing platform (9:16 for TikTok/shorts, 16:9 for YouTube).
• Start with 5s runs for fast iteration; expand to 10s for final sequences.
• Use camera_fixed for product showcases, interviews, or static shots.
• Keep seeds fixed if you need consistent multi-shot content.

Use Cases

• Creative video content generation
• Prototype development for film and animation
• Commercial video production
• Educational and documentary content
• Fantasy and surreal video creation

Notes

• Performance metrics based on specific benchmark datasets
• Actual generation quality may vary with prompt complexity
• Multi-shot consistency depends on prompt clarity and scene descriptions

Authentication

For authentication details, please refer to the Authentication Guide.

API Endpoints

Submit Task & Query Result

set -euo pipefail

export WAVESPEED_API_KEY="your-api-key"

REQUEST_BODY=$(cat <<'JSON'
{
  "prompt": "A cinematic ocean wave at sunrise, highly detailed",
  "aspect_ratio": "16:9",
  "duration": 5,
  "camera_fixed": false
}
JSON
)

# 1. Submit the prediction once. Never retry this request automatically:
# a retry after an unclear failure can create a second, billed task.
CHECK='The task may already exist. Check History or the predictions list before submitting again.'
if ! SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  --connect-timeout 10 --max-time 60 \
  -X POST "https://api.wavespeed.ai/api/v3/bytedance/seedance-v1-pro-t2v-480p" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}"); then
  printf 'Submit failed. %s\n' "${CHECK}" >&2
  exit 1
fi

TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id. %s\n' "${CHECK}" >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction reaches a final status.
BODY_FILE=$(mktemp)
trap 'rm -f "${BODY_FILE}"' EXIT
while true; do
  # Transient errors (429, 5xx) are retried, honoring Retry-After.
  HTTP_CODE=$(curl --silent --show-error --fail-with-body \
    --connect-timeout 10 --max-time 60 --retry 5 --retry-delay 2 \
    --output "${BODY_FILE}" --write-out '%{http_code}' \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}" || true)
  case "${HTTP_CODE}" in
    2??) ;;
    000|429|5??)  # dropped connection or temporary error: keep polling
      printf 'Task %s: HTTP %s, polling again in 10s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      sleep 10; continue ;;
    *) printf 'Task %s: HTTP %s\n' "${PREDICTION_ID}" "${HTTP_CODE}" >&2
      cat "${BODY_FILE}" >&2; exit 1 ;;
  esac
  RESULT=$(jq 'if type == "object" and has("data") then .data else . end' "${BODY_FILE}")
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

  case "${STATUS}" in
    completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
    failed|cancelled|timeout|deleted)
      printf 'Task %s ended with status %s\n' "${PREDICTION_ID}" "${STATUS}" >&2
      printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    *) sleep 2 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Every model also accepts the global request options enable_sync_mode and enable_base64_output; see their pages for details.

Response Parameters

Result Request Parameters

Result Response Parameters