Bytedance Seedance 2.5 Flash Text To Video Turbo API Documentation

Bytedance Seedance 2.5 Flash Text To Video Turbo API Documentation

Playground

Seedance 2.5 Flash Text-to-Video Turbo creates videos from text prompts and optional image, video, and audio references, with 720p or 1080p output and optional generated audio. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Seedance 2.5 Flash Text-to-Video Turbo generates cinematic videos from text prompts, with optional reference images, videos and audio. Choose a duration of 4 to 30 seconds, 720p or 1080p output, and optional synchronized audio.

> Turbo: this tier generates at 480p and upscales the result to your chosen resolution, which makes it faster and cheaper than the standard tier. Use the standard product for native quality, or for 4k.

Why Choose This?

• Native audio
  Enable audio generation for dialogue, sound effects and ambience.

• Director-style prompt control
  Direct camera movement, lighting, performance, atmosphere and pacing through the prompt.

• Up to 30 seconds
  Generate clips from 4 to 30 seconds in one request.

• 720p or 1080p output
  Choose the resolution that fits the job. The video is generated at 480p and upscaled.

Parameters

How to Use

1. Write your prompt: describe the subject, action, camera movement, lighting and mood.
2. Set duration and resolution: 4–30 seconds, 720p or 1080p.
3. Add references (optional): use reference images, videos and audio, and bind each one in the prompt by upload order.
4. Submit and retrieve the output URL.

Pricing

Output only

Pricing is based on the selected generation duration, from 4 to 30 whole seconds.

With reference videos

The reference-video duration and the generation duration are charged at $0.075 per second, plus an upscale fee of $0.02 per generated second at 720p or $0.04 at 1080p. Each reference video is counted as at least 2 seconds, each clip and the combined input are capped at 30 seconds, and the combined input duration is rounded up to a whole second.

Best Use Cases

• Ad and social creative: test concepts and produce short clips in volume.
• Concept visualization: turn ideas into motion previews for pitching and storyboarding.
• Audio-driven scenes: clips with synchronized sound for ambience, music or narrative moments.

Pro Tips

• Write prompts like a shot list: subject, action, camera, lighting, mood.
• Use 16:9 for widescreen and 9:16 for vertical social content.
• Start with a short duration while testing a prompt, then lengthen once the direction works.
• Bind reference media explicitly in the prompt, for example @Image 1, @Video 1, @Audio 1.

Related Models

• Seedance 2.5 Text-to-Video: 720p or 1080p output.
• Seedance 2.5 Image-to-Video: generate video from a start image.
• Seedance 2.5 Video Edit: edit an existing video with a prompt.

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",
  "resolution": "720p",
  "duration": 5,
  "generate_audio": true
}
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-2.5-flash/text-to-video-turbo" \
  -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