Kling 3.0 API

Introduction

Kling 3.0 Text to video turns a written prompt into a clip with no image or driving video involved. Set a length from 3 to 15 whole seconds, a resolution of 720p, 1080p or 4K, and an aspect ratio of 16:9, 9:16 or 1:1. Turn generate_audio on to get dialogue, effects and ambience generated in the same pass, and choose shot_type to keep one continuous setup or let Kling cut its own multi-shot edit.

Choose a Kling 3.0 mode by starting material

Key features

Dialogue and ambience in the same file

With generate_audio on, a spoken line written in quotes in the prompt comes back as audible dialogue, timed to the picture, alongside whatever ambient sound you describe. In our test the line "Don't wait up" came back spoken over a string quartet and the murmur of a gala, all from one paragraph.

Two ways to handle multiple shots

shot_type set to single keeps the camera on one setup for most of the run, though it can still cut on its own - in our tests two single-shot clips picked up an extra cut mid-run, once with the light changing across it. Adding "one continuous shot, no cuts" to the prompt held the shot together in our retest. Set shot_type to multi and Kling decides its own cuts instead.

720p, 1080p and 4K

Draft the timing and framing at 720p, then run the take you like at 4K once it is worth the render.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

Each task is rounded up to whole credits, so one run at the lowest tier costs 51 credits for a 5-second clip ($0.51).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Open a scene with real sound

A toast, a confession, a goodbye - write the line and turn audio on, and the dialogue, the room tone and the picture arrive in one file. Our rooftop-party example ends on a whole group shouting one line together, timed against the clinking bottles and music underneath it.

Draft a look before committing to 4K

Text-to-video needs no source image, so it is the fastest way to test a lighting idea, a camera move or a piece of dialogue before spending a 4K render on it.

Hand off to image-to-video for continuity

Text-to-video decides wardrobe, face and framing fresh on every run. When a character has to look the same across several clips, generate the first shot here, then take its final frame into image-to-video as the opening frame of the next one.

Prompt guide & pro tips

Write it in the order it happens

Structure the prompt as subject and wardrobe, action, camera move, look, then sound. The palazzo-terrace-gown example follows that order: who she is and what she wears, what she does (walks, turns, speaks), the camera and light, then the ambient sound.

Give the whole group one line to land on

When several people are on screen, naming a single moment - one line, spoken together, at the very end of the brief - gives the model a clear beat to land the dialogue on instead of guessing when several voices should overlap.

Say "one continuous shot, no cuts" when it matters

shot_type: single is not a hard guarantee against cuts. If the take must hold one setup all the way through, add that instruction directly in the prompt; it held both the framing and the lighting steady in our retest of a shot that had cut and changed light on the first attempt.

API quick start

Call the Kling 3.0 API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model kling/3.0/text-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "kling/3.0/text-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration_seconds": 5,
    "shot_type": "single"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Kling 3.0 API questions

All Kling models

Kling O3 is the more flexible sibling: up to seven reference photos in one shot, automatic multi-shot cuts, and editing of clips you already have. Kling 3.0 is the pick for a single polished shot with first and last frames or Motion Control.

• Kling 3.0 API4K clips, multi-shot cuts and motion controlFrom 51 credits for a 5-second clip
• Kling O3 APIKling’s unified model: create, animate, reference and edit up to 4KFrom 51 credits for a 5-second clip
• Kling 3.0 Turbo APIFaster Kling 3.0 with sound on every clipFrom 84 credits for a 5-second clip
• Kling Avatar 2.0 APIA portrait that speaks or sings your audio, up to 5 minutesFrom 7.68 credits per second
• Kling 2.6 API1080p clips with optional sound and motion controlFrom 52 credits for a 5-second clip
• Kling 2.5 Turbo API1080p clips with a soundtrack on every takeFrom 42 credits for a 5-second clip
• Kling 2.1 Master APISilent 1080p clips with fine prompt controlFrom 162 credits for a 5-second clip
• Kling 2.1 APIAnimate a frame at 720p or 1080p, with an optional end frameFrom 27 credits for a 5-second clip

Other video APIs

• MiniMax H3 APIExpressive clips with audio, up to 2KFrom 28 credits for a 5-second clip
• Seedance 2.5 APIByteDance's newest: 30-second clips with native audioFrom 56 credits for a 5-second clip
• Vidu Q4 Preview APIUp to 4K clips with sound and spoken dialogueFrom 34 credits for a 5-second clip
• Wan 3.0 APIUp to 30-second clips with synced audioFrom 34 credits for a 5-second clip
• MiniMax H3 Max APIFast clips with ambience, effects and musicFrom 38 credits for a 5-second clip
• LTX 2.5 APILong 20-second takes up to 4K with a soundtrackFrom 68 credits for a 5-second clip

More about Kling 3.0

Try it

Kling 3.0 AI Video Generator onlineCreate videos with Kling 3.0 in PopNow

Compare

Kling 3.0 vs Seedance 2.5Kling 3.0 vs Wan 3.0Kling 3.0 vs Kling O3Kling 3.0 vs MiniMax H3

Docs

Kling 3.0 model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage to video guide for the PopNow APIWebhooks: get Kling 3.0 results without polling