kwaivgi/kling-video/v2.6/pro/text-to-video
Kling Video V2.6 Pro by KwaiVGI - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runkwaivgi/kling-video/v2.6/pro/text-to-videoInput Schema
4 parameters · 1 required · 3 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | Max length: 2500 |
duration | integer | Optional | The duration of the generated video in seconds · Options: 5, 10 · Default: 5 510 |
aspect_ratio | string | Optional | The aspect ratio of the generated image. · Options: 16:9, 9:16, 1:1 16:99:161:1 |
generate_audio | boolean | Optional | Whether to generate native audio for the video. Supports Chinese and English voice output. Other languages are automatically translated to English. For English speech, use lowercase letters; for acronyms or proper nouns, use uppercase. · Default: true |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "kwaivgi/kling-video/v2.6/pro/text-to-video",
"prompt": "Old friends reuniting at a train station after 20 years, one exclaims 'Is that really you?!' other tearfully replies 'I promised I'd come back, didn't I?', train whistle, steam hissing, emotional orchestral swell, crowd murmur",
"duration": 5,
"generate_audio": true
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Kling Video V2.6 Pro Text-to-Video
Kling Video V2.6 Pro Text-to-Video creates a complete short clip from one written scene. The request starts with a prompt and can add duration, frame shape, and an audio toggle without requiring any visual input. The returned video can include spoken lines, environmental sound, and music cues described in the prompt.
The route offers fixed 5- and 10-second outputs in landscape, portrait, or square format. This makes it a focused choice for self-contained scenes whose picture and sound should be planned together. Its compact contract keeps the workflow centered on a single creative brief.
Highlights
- Cinematic generation from text. The exact V2.6 Pro route is positioned for cinematic visuals. It creates the scene without requiring a starting frame.
- Fluid, consistent motion. Fluid motion is part of the route's stated capability. V2.6 documentation also identifies improved motion consistency.
- Native audio synthesis. Audio can be generated together with the video. Chinese and English voice output are supported locally, with other languages translated to English.
- Visual quality focus. The V2.6 text-to-video documentation identifies improved visual quality.
Pricing
| Duration | Price |
|---|---|
| 5 seconds | $0.70 |
| 10 seconds | $1.40 |
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| Produce a dialogue moment from a script without filming actors. | Preserve a particular opening composition; use image-to-video. |
| Create an atmospheric scene with ambience, effects, and music cues. | Need voice behavior outside the documented language handling. |
| Make a five-second teaser or visual beat. | Need a duration other than 5 or 10 seconds. |
| Use ten seconds for a complete action and response. | Need several separately prompted shots in one request. |
| Deliver the same concept for landscape, vertical, or square placement. | Need a frame shape outside the documented set. |
Prompt Guide
Write the scene in temporal order. Name the visible action and camera movement, then include dialogue, ambience, and music cues when audio is enabled.
Scene: [place, time, atmosphere]
Characters: [appearance and action]
Camera: [framing and movement]
Dialogue: [exact spoken lines]
Sound: [ambience, effects, music]
Ending: [final action or frame]
{
"prompt": "Old friends reunite at a train station after 20 years. One exclaims 'Is that really you?!' and the other replies 'I promised I'd come back, didn't I?' A train whistle, steam, crowd murmur, and an emotional orchestral swell accompany the scene.",
"duration": 5,
"aspect_ratio": "16:9",
"generate_audio": true
}
Technical Specs
| Spec | Value |
|---|---|
| Required input | prompt |
| Prompt length | Up to 2,500 characters |
| Duration | 5 or 10 seconds; default 5 |
| Aspect ratios | 16:9, 9:16, 1:1 |
| Native audio | Optional; default enabled |
| Voice behavior | Chinese and English; other languages translated to English |
| Output | Video URL with optional file metadata |
Related
- Kling Video V2.6 Pro Image-to-Video — Animate a supplied image.
- Kling Video V3 Pro Text-to-Video — Use the newer V3 text-led route.