One uninterrupted three-second low side-view shot inside a dry ancient lava tube, no active lava. An adult cave explorer in a muted red protective suit and white helmet makes one careful short step across a shallow narrow groove on the basalt floor. The attached headlamp sweeps naturally across rough dark rock as the body moves; feet land firmly, arms remain stable. Controlled subtle camera tracking, realistic headlamp falloff and deep shadows, detailed basalt. No jumps, extra people, cuts, text or logos.
Kling 3.0 Pro Text to Video API
kwaivgi/kling-v3.0-pro/text-to-videoKling 3.0 Pro Text to Video builds 1080p scenes from prompts, combining native audio with shot-by-shot direction. Specify the action, framing and lighting in each shot to guide the story and its visual continuity.
Input
Write one prompt per shot and choose 1–12 seconds for each. The total must be 3–15 seconds; Sound stays on.
259/2,500
362/2,500
Duration: 3 s (3-15)
Output
Video readyExplore another workflow
Examples
REST API
Quick Start
Submit a Kling 3.0 Pro Text to Video request and use its task identifier to retrieve the video.
01
Authentication
Send your Vidgo API key in the Authorization header as a Bearer token.
- Submit endpoint
- POST
https://api.vidgo.ai/api/generate/submit - Authentication
- Authorization: Bearer YOUR_API_KEY
02
Submit Request
Send the model identifier and scene prompt inside the JSON request. Change the prompt to describe your scene.
Request example
REQUEST_BODY=$(cat <<'JSON'
{
"model": "kwaivgi/kling-v3.0-pro/text-to-video",
"input": {
"prompt": "A ceramic cup sits beside a window in morning light. The camera slowly moves closer as steam curls above the rim. A quiet room tone accompanies the scene.",
"duration": 5,
"multi_shots": false,
"sound": true,
"aspect_ratio": "16:9"
}
}
JSON
)
RESPONSE=$(curl --silent --show-error --fail-with-body \
--request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data "$REQUEST_BODY")
CODE=$(printf '%s' "$RESPONSE" | jq -r '.code // empty')
if [ "$CODE" != "0" ] && [ "$CODE" != "200" ]; then
printf 'API error: %s
' "$RESPONSE" >&2
exit 1
fi
printf '%s
' "$RESPONSE"03
Query Task Status
Replace {task_id} in the status URL with the identifier returned on submission.
Status endpoint
https://api.vidgo.ai/api/generate/status/{task_id}Query this URL with the returned task_id. Continue until finished or failed; a completed video is listed in data.files.
not_startedrunningfinishedfailedSubmission response
{
"code": 200,
"data": {
"task_id": "example-task-id",
"status": "not_started",
"created_time": "2026-09-27T00:00:00Z"
}
}Completed response
{
"code": 200,
"data": {
"task_id": "example-task-id",
"status": "finished",
"created_time": "2026-09-27T00:00:00Z",
"files": [
{
"file_type": "video",
"file_url": "https://example.com/generated-video.mp4"
}
]
}
}Complete Example
When status is finished, read file_url from video entries in files. Task IDs and output URLs below illustrate the response format.
Complete Example
set -euo pipefail
: "${VIDGO_API_KEY:?Set VIDGO_API_KEY in your environment}"
REQUEST_BODY=$(cat <<'JSON'
{
"model": "kwaivgi/kling-v3.0-pro/text-to-video",
"input": {
"prompt": "A ceramic cup sits beside a window in morning light. The camera slowly moves closer as steam curls above the rim. A quiet room tone accompanies the scene.",
"duration": 5,
"multi_shots": false,
"sound": true,
"aspect_ratio": "16:9"
}
}
JSON
)
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
--request POST \
--url "https://api.vidgo.ai/api/generate/submit" \
--header "Authorization: Bearer $VIDGO_API_KEY" \
--header "Content-Type: application/json" \
--data "$REQUEST_BODY")
TASK_ID=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.data.task_id // .task_id // empty')
BUSINESS_CODE=$(printf '%s' "$SUBMIT_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
printf 'Submit failed:
%s
' "$SUBMIT_RESPONSE" >&2
exit 1
fi
if [ -z "$TASK_ID" ]; then
printf 'Submit response did not include task_id:
%s
' "$SUBMIT_RESPONSE" >&2
exit 1
fi
START_TIME=$(date +%s)
POLL_DELAY=2
while true; do
if [ $(( $(date +%s) - START_TIME )) -ge 600 ]; then
printf 'Timed out after 600 seconds
' >&2
exit 1
fi
STATUS_RESPONSE=$(curl --silent --show-error --fail-with-body \
--url "https://api.vidgo.ai/api/generate/status/$TASK_ID" \
--header "Authorization: Bearer $VIDGO_API_KEY")
STATUS=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.data.status // .status // empty')
BUSINESS_CODE=$(printf '%s' "$STATUS_RESPONSE" | jq -r '.code // empty')
if [ "$BUSINESS_CODE" != "0" ] && [ "$BUSINESS_CODE" != "200" ]; then
printf 'Status request failed:
%s
' "$STATUS_RESPONSE" >&2
exit 1
fi
case "$STATUS" in
finished)
printf '%s' "$STATUS_RESPONSE" | jq -r '(.data.files // .files // [])[]?.file_url'
break
;;
failed)
printf '%s' "$STATUS_RESPONSE" | jq -r '.data.error_message // .error_message // "Generation failed"' >&2
exit 1
;;
not_started|running)
sleep "$POLL_DELAY"
if [ "$POLL_DELAY" -lt 10 ]; then POLL_DELAY=$((POLL_DELAY + 1)); fi
;;
*)
printf 'Unexpected task status: %s
' "$STATUS" >&2
exit 1
;;
esac
doneRequest Parameters
Choose a single prompt or a sequence of shots, then set duration and sound for this endpoint.
| Field | Type | Requirement | Default | Usage |
|---|---|---|---|---|
| prompt | string | When multi_shots=false | Set explicitly | Describe the subject, scene and camera direction in 1–2,500 characters. For multiple shots, write each scene in multi_prompt. |
| multi_shots | boolean | Optional | false | Choose false for one prompt, or true for separately timed shots with multi_prompt and sound=true. |
| multi_prompt | object[] | When multi_shots=true | Set explicitly | Add at least one object with prompt and duration. Each prompt uses 1–2,500 characters; each shot lasts 1–12 integer seconds. Shot times add up to duration. |
| duration | integer | Required | Set explicitly | Set the total clip length to an integer from 3 to 15 seconds. For multiple shots, use the sum of their durations. |
| sound | boolean | Optional | true | Use true for generated audio. A silent single shot uses false. Multiple shots use true. |
| aspect_ratio | string | Optional | 1:1 | Choose 1:1, 16:9 or 9:16 to frame square, landscape or portrait scenes. |
Response Fields
Submission returns a task identifier. Query its status to retrieve generated video URLs.
| Field | Type | Usage |
|---|---|---|
| code | integer | Response code: 0 or 200 indicates a successful API operation. |
| data.task_id | string | Identifier returned on submission; use it to query the same task. |
| data.status | string | One of not_started, running, finished or failed. A successful submission is followed by status checks. |
| data.created_time | string | Task creation time returned by the service. |
| data.files | array | Generated media entries returned when the task finishes. |
| data.files[].file_type | string | Use entries with file_type=video for the generated clip. |
| data.files[].file_url | string | Video URL for playback or download. |
| data.error_message | string | null | Read the task error detail when status=failed. |
Task Lifecycle
Keep the returned task_id and follow status until finished or failed.
not_startedThe request is accepted and waiting to start. Keep its task_id for the next status check.
runningThe video is being generated. Continue checking the same task.
finishedGeneration is complete. Read the video entries in files.
failedGeneration ended with an error. Review error_message before submitting an adjusted request.
Error Handling
- Check timing before submittingFor multiple shots, use sound=true and ensure individual durations sum to a total of 3–15 seconds.
- Keep reference URLs accessibleUse public HTTP(S) media URLs that remain reachable while the task is processed.
- Resume interrupted status checksIf a status request fails, retry the status check using the same task_id. Submit a new generation only when you intend to create another clip.
- Read the returned errorFor a failed task, inspect error_message and adjust the relevant input before trying again.
Specifications
| Specification | Value | Usage |
|---|---|---|
| Input mode | Text to Video | One scene prompt or a sequence of individually timed shot prompts. |
| Resolution | 1080p | 1080p video output for this tier. |
| Clip duration | 3–15 seconds | Whole seconds; each shot in a sequence uses 1–12 seconds. |
| Audio | sound | Generate audio with true; single-shot silent generation uses false. |
| Model identifier | kwaivgi/kling-v3.0-pro/text-to-video | Public model value for this request. |
Related Models
Kling 3.0 Pro Text to Video API frequently asked questions
What is the Kling 3.0 Pro Text to Video API?
Kling 3.0 Pro Text to Video is a Kuaishou model for generating scenes from written prompts. It creates 1080p footage with audio and individually timed shots. Joint audio and video generation connects sound with the scene, while per-shot prompts guide its action and continuity. You can call it programmatically or try it from the playground above.
How can Kling 3.0 Pro Text to Video stage a conversation?
Assign each speaker a clear description and put the spoken line next to that speaker’s action. With sound=true, a multi-shot request can give the opening, reply and reaction separate prompts and durations within a 3–15 second scene.
How do I add audio in Kling 3.0 Pro Text to Video?
Set sound=true and describe the desired dialogue, ambient sound or effects alongside the visual action. Single shots can use sound=false for silent footage; multi-shot sequences use sound=true.
How should I describe close-ups for Kling 3.0 Pro Text to Video?
Name the feature that matters, such as a face or a product surface, then specify framing, lighting and movement. Pro generates 1080p footage, so choose a composition that makes the important detail visible rather than placing it in a distant background.
How do I guide scene continuity in Kling 3.0 Pro Text to Video?
Repeat the same character traits, clothing, setting and lighting across shot prompts. Change the action or camera angle deliberately so the next shot has a clear relationship to the previous one.
How do shot durations shape Kling 3.0 Pro Text to Video pacing?
Set each shot to 1–12 integer seconds and keep the total between 3 and 15 seconds. Give a spoken line, a gesture and a reaction distinct time allocations; set duration to their sum and keep sound=true.
When should I choose Kling 3.0 Pro over Kling 3.0 Standard?
Choose Pro for 1080p footage where faces, props or backgrounds benefit from the higher output resolution. Standard provides 720p for lower-cost scene exploration.
How does Sound affect Kling 3.0 Pro billing?
Silent single shots cost $0.195 per second; clips with audio cost $0.245 per second. Multiply the selected rate by total duration. Multiple shots use the audio rate and their combined length.