Kwaivgi Kling V2.5 Turbo Pro Text To Video

Kwaivgi Kling V2.5 Turbo Pro Text To Video

Playground

Kling 2.5 Turbo Pro is a Text-to-Video model that delivers cinematic visuals, fluid motion, and precise prompt-to-motion responsiveness. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

Kling 2.5 Turbo Pro is an advanced text-to-video model that produces ultra-smooth motion, cinematic visuals, and accurate prompt adherence.

Its improved dynamic processing and text-to-motion control allow for seamless transitions while maintaining style fidelity across various looks.

What makes it different?

• Enhanced multi-step instruction understanding A new text-and-timing controller processes multi-step prompts to transform static inputs into coherent, controllable narrative scenes.

• High-motion quality and stability Better training and data balance create realistic dynamics, enabling quick and complex movements with fewer artifacts like jitter, tearing, or frame drops.

• Faster inference Optimized pipelines reduce end-to-end delay, providing faster delivery of high-quality results without compromising visual fidelity.

• Consistent style Enhanced style conditioning preserves the reference look (palette, lighting, brushwork, mood), ensuring frames stay consistent - even during dynamic scenes.

Designed for

• Marketing & Brand Teams – Produce style-consistent ads, feature demos, and campaign assets fast.
• Content Creators / YouTubers / Short-form Teams – Improve watch-through with stronger narrative flow and motion.
• Film/Animation Studios – Use for previz, technique exploration, and style studies with reliable dynamic consistency.
• Training & Education – Turn documents into clear, high-resolution explainer videos for scalable distribution.

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 the prompt – Specify subject, scene, actions, camera movement, and style keywords; include multi-step/causal logic if needed.

2. Choose aspect – Match output to your channel and quality targets.

3. Set duration – Help models understand how long of the result.

4. Set guidance_scale – Controls how strongly the model follows your prompt. The higher the value, the less creative freedom the model has.

5. Generate – Leverage accelerated inference to get a first pass quickly.

6. Review & iterate – Refine timing, angles, or style strength and re-render for final delivery (Set the seed).

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,
  "guidance_scale": 0.5
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v2.5-turbo-pro/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