Vidu Text To Video 2.0 API Documentation

Vidu Text To Video 2.0 API Documentation

Playground

Vidu Text-to-Video 2.0 converts text prompts into high-quality 720p videos with exceptional visual detail and diverse motion dynamics. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Vidu Text-to-Video 2.0 turns your imagination into motion — a next-generation text-to-video model that produces cinematic 720p videos with smooth, expressive, and visually coherent motion. Now with flexible duration control, you can generate 5s or 8s clips for storytelling, concept visualization, or creative motion studies.

🌟 Why it looks amazing

• Cinematic realism: generates film-like motion, lighting, and depth of field.
• Temporal consistency: prevents flicker and ghosting between frames.
• Expressive movement: animates both camera and subject naturally for lifelike motion.
• Scene understanding: interprets your text prompt accurately to match composition, emotion, and action.
• 720p output: crisp visuals ready for editing, sharing, or production use.

⚙️ Parameters and Controls

• prompt — describe your scene (e.g., “A woman walking through a rainy street under neon lights”).

• auto (default): automatically adjusts motion scale.

• small: subtle, gentle movements (good for portraits or static shots).

• medium: balanced motion, ideal for everyday scenes.

• large: dramatic, cinematic camera or subject motion.

• duration — select video length:

• 5: short clips, ideal for previews or teasers.

• 8: extended motion for storytelling or scene development.

• seed — use a fixed number for reproducibility or leave empty for random generation.

💰 Pricing

🚀 How to Use

1. ✍️ Write your prompt describing the scene or story. 2.3. ⏱️ Select duration (5 or 8 seconds).
2. 🎲 Optionally set a seed for reproducibility.
3. ▶️ Click Run to generate your cinematic video.

💡 Pro Tips

• Keep prompts concise but descriptive — include subject, setting, and atmosphere.
• Choose 8s duration for narrative continuity or action sequences.
• Experiment with different seeds to explore creative variations.

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",
  "duration": 5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/vidu/text-to-video-2.0" \
  -H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
  -H "Content-Type: application/json" \
  -d "${REQUEST_BODY}")

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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body \
    "${RESULT_URL}" \
    -H "Authorization: Bearer ${WAVESPEED_API_KEY}")
  RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
  STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')

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

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters