Kling V3 Turbo Pro converts first-frame images and optional prompts into high quality 1080P videos with fast pro-tier inference and multi-shot storyboard support. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Idle
$0.14per run·~71 / $10
Pages fly out from the shelves and spiral into the portal. The student reaches for one floating page, the library clock spins backward, and the camera rotates slightly as the room bends around him.
Kling V3 Turbo Pro Image-to-Video generates high quality 1080p videos from a first-frame reference image. It supports optional text guidance and multi-shot storyboard generation.
First-frame image animation
Turn a still image into a high quality video using the image as the starting frame.
High quality 1080p output
Use the pro-tier model for stronger detail and visual quality.
Optional prompt guidance
Add a prompt to guide motion, camera movement, and scene behavior.
Multi-shot storyboard support
Use multi_prompt to define multiple prompted segments with separate durations.
Standard video output
The generated video is returned as a URL in the standard WaveSpeed prediction response.
| Parameter | Required | Description |
|---|---|---|
| image | Yes | First-frame reference image URL. JPG and PNG images work best. |
| prompt | No | Optional text prompt to guide the generated video. Mutually exclusive with multi_prompt. |
| multi_prompt | No | Multi-shot storyboard. Each item includes a prompt and duration. Mutually exclusive with prompt. |
| duration | No | Total video duration in seconds. Options: 3 to 15. Default: 5. For multi_prompt, shot durations must sum to this value. |
multi_prompt to define multiple prompted segments.multi_prompt, set each shot duration so their sum equals the selected total.Returns generated video URL(s) in the standard WaveSpeed prediction response.
The generated video is returned as MP4 video.
Pricing is $0.14 per second.
WaveSpeed bills by the selected total duration. For multi_prompt, shot durations must sum to that total; they are not added again for billing.
| Generated Duration | Price |
|---|---|
| 3s | $0.42 |
| 5s | $0.70 |
| 10s | $1.40 |
| 15s | $2.10 |
duration parameter is the total generated video duration.multi_prompt, shot durations must sum to duration; billing does not add them a second time.multi_prompt when you want multiple guided segments.multi_prompt shot durations sum exactly to the selected total duration.image is required.prompt is optional.prompt and multi_prompt are mutually exclusive.duration is the total video duration for both single-prompt and multi_prompt generation.multi_prompt supports per-shot durations.multi_prompt, the shot durations must sum exactly to the selected duration (3–15 seconds).Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/kwaivgi/kling-v3-turbo-pro/image-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Kling v3 Turbo Pro Image To Video below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": 5,
"cfg_scale": 0.5
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v3-turbo-pro/image-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; 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' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$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
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/kwaivgi/kling-v3-turbo-pro/image-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": 5,
"cfg_scale": 0.5
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": 5,
"cfg_scale": 0.5
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/kwaivgi/kling-v3-turbo-pro/image-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Kling v3 Turbo Pro Image To Video is a Kuaishou model for video generation from images, exposed as a REST API on WaveSpeedAI. Kling V3 Turbo Pro converts first-frame images and optional prompts into high quality 1080P videos with fast pro-tier inference and multi-shot storyboard support. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v3-turbo-pro-image-to-video.
Kling v3 Turbo Pro Image To Video starts at $0.14 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `image`, `duration`, `cfg_scale`, `multi_prompt`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/kwaivgi/kwaivgi-kling-v3-turbo-pro-image-to-video.
Median end-to-end generation time on WaveSpeedAI is around 134 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (Kuaishou). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.