Vidu Text To Video

Vidu Text To Video

Playground

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

Features

Vidu Text-to-Video transforms your text prompts into high-quality, cinematic 720p videos — complete with expressive motion, dynamic lighting, and natural camera movement. Built for creators, storytellers, and developers, Vidu delivers smooth, detailed, and visually coherent motion sequences directly from text input.

🌟 Why it looks amazing

• Cinematic generation: produces film-like shots with realistic motion and depth of field.
• High temporal consistency: ensures clean transitions with minimal flicker or distortion.
• Motion diversity: supports subtle gestures, expressive movement, and camera motion for natural flow.
• Text-guided direction: interprets complex scene descriptions with strong semantic alignment.
• 720p output: optimized for crisp detail and creative flexibility.

⚙️ Parameters and Controls

• prompt — describe your scene (e.g., “A cat walking through a neon-lit alley at night”).

• movement_amplitude — control motion strength:

• auto (default): model decides best motion level.

• small: subtle, gentle movements (good for portraits or still scenes).

• medium: balanced camera and subject motion.

• large: cinematic, dramatic, or action-heavy movement.

• seed — set for reproducible results (leave blank for random).

💰 Pricing

🚀 How to Use

1. ✍️ Write your prompt describing the scene or action.
2. 🎥 Choose your movement amplitude (auto, small, medium, or large).
3. 🎲 Optionally set a seed for reproducibility.
4. ▶️ Click Run ($0.20) to generate your video.

💡 Pro Tips

• Use vivid verbs and adjectives for better motion understanding.
• For subtle portraits, pick small amplitude; for dynamic shots, choose large.
• Keep your prompt concise but descriptive — focus on subject, setting, and style.
• Adjust seed values to explore different visual interpretations of the same 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",
  "movement_amplitude": "auto"
}
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" \
  -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 "${PREDICTION_ID}" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi

# 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) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
  esac
done

Parameters

Task Submission Parameters

Request Parameters

Response Parameters

Result Request Parameters

Result Response Parameters