Kling v2.6 Text-to-Video
Kling v2.6 Text-to-Video generates video with native audio from text prompts alone. It supports multi-shot narrative storytelling with synchronized speech, sound effects, and ambient audio at up to 1080p in a single request. Your use is subject to Kling AI's Terms & Privacy Policies.
View API reference- Price
- $0.04, Per secondLowest available configuration
import { experimental_generateVideo as generateVideo } from 'ai';
const result = await generateVideo({ model: 'klingai/kling-v2.6-t2v', prompt: 'A serene mountain lake at sunrise.'});Copy link to headingPlayground
Try out Kling v2.6 Text-to-Video by Kling AI. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Kling v2.6 Text-to-Video
Your generated video will appear here.
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Getting started
Generate videos with Kling v2.6 Text-to-Video using the experimental_generateVideo function from AI SDK 6 or later. AI Gateway handles routing and polls until the video is ready.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the video generation quickstart.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'klingai/kling-v2.6-t2v', prompt: 'A chicken flying into the sunset in the style of 90s anime', providerOptions: { klingai: { mode: 'std', }, }, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);Top-level parameters
Exercise the supported top-level parameters: prompt, aspectRatio, and duration.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'klingai/kling-v2.6-t2v', prompt: 'A chicken flying into the sunset in the style of 90s anime', aspectRatio: '16:9', duration: 5, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Yes | Text description of the video to generate. Max 2500 characters. |
duration | 5 | 10 | No | Video length in seconds. 5 or 10 seconds. |
resolution | string | No | Resolution ('1280x720', '1920x1080'). |
aspectRatio | string | No | Aspect ratio ('16:9', '9:16', '1:1'). |
generateAudio | boolean | No | Generate synchronized audio with the video. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Up to 2500 characters |
Provider options
Load the always-compatible KlingAI options under providerOptions.klingai. Feature controls like cameraControl, voiceList, and multiShot are mutually exclusive with each other and are shown in their own examples below.
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'klingai/kling-v2.6-t2v', prompt: 'A chicken flying into the sunset in the style of 90s anime', aspectRatio: '16:9', duration: 5, generateAudio: true, providerOptions: { klingai: { mode: 'pro', negativePrompt: 'blurry, low quality', watermarkEnabled: true, pollIntervalMs: 5000, pollTimeoutMs: 600000, }, }, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);Pass KlingAI-specific options under providerOptions.klingai in your generateVideo call.
| Parameter | Type | Required | Description |
|---|---|---|---|
mode | 'std' | 'pro' | No | 'std' for standard quality. 'pro' for professional quality. Defaults to 'std'. |
negativePrompt | string | No | What to avoid in the video. Max 2500 characters. |
voiceList | array | No | Voice IDs for speech. Max 2 voices. Requires generateAudio: true. Cannot coexist with elementList. |
cameraControl.type | string | No | Camera movement type: 'simple', 'down_back', 'forward_up', 'right_turn_forward', or 'left_turn_forward'. |
cameraControl.config | object | No | Movement configuration. Required when type is 'simple'. Set one of horizontal, vertical, pan, tilt, roll, or zoom in range [-10, 10] and leave the others at 0. |
watermarkEnabled | boolean | No | Generate a watermarked result alongside the video. |
pollIntervalMs | number | No | How often to check task status. Defaults to 5000. |
pollTimeoutMs | number | No | Maximum wait time. Defaults to 600000 (10 minutes). |
Audio and voice
Set generateAudio: true to enable audio.
Reference voices in your prompt with the <<<voice_1>>> syntax, where the number matches the order of entries in voiceList. You can use up to 2 voices per video, and voice generation requires generateAudio: true.
Camera control
Control camera movement during generation. Use a preset movement type or 'simple' with a config that sets one axis (others stay at 0).
import { experimental_generateVideo as generateVideo } from 'ai';import fs from 'node:fs';import 'dotenv/config';
async function main() { const result = await generateVideo({ model: 'klingai/kling-v2.6-t2v', prompt: 'A serene mountain landscape at sunset', aspectRatio: '16:9', providerOptions: { klingai: { mode: 'std', cameraControl: { type: 'simple', config: { zoom: 5, horizontal: 0, vertical: 0, pan: 0, tilt: 0, roll: 0, }, }, }, }, });
// Save the generated video fs.writeFileSync('output.mp4', result.videos[0].uint8Array);
console.log('Video saved to output.mp4');}
main().catch(console.error);Copy link to headingMore models by Kling AI
| Model |
|---|
| — | $0.13/sec+1 more | — | | 03/04/2026 | ||||||||||
| — | $0.17/sec+1 more | — | | 02/05/2026 | ||||||||||
| — | $0.07/sec+1 more | — | | 12/18/2025 | ||||||||||
| — | $0.04/sec+1 more | — | | 12/03/2025 | ||||||||||
| — | $0.04/sec+1 more | — | | 09/23/2025 | ||||||||||
| — | $0.04/sec+1 more | — | | 09/23/2025 |
Copy link to headingAbout Kling v2.6 Text-to-Video
Kling v2.6 Text-to-Video introduces multi-shot storytelling as a core capability. Earlier Kling text-to-video generations produced a single continuous scene. V2.6 interprets a prompt describing sequential events and generates distinct scene cuts within the output duration. This suits narrative content: an advertisement with a product reveal followed by a lifestyle shot, an educational clip moving through two or three steps, or a social post telling a mini-story.
Native audio generation accompanies this multi-shot capability. Speech synthesis in Chinese and English, sound effects synchronized to on-screen action, and environmental ambient audio all produce in the same inference pass as the video frames. The result is a finished audio-visual asset from a text prompt, with no post-processing alignment needed.
V2.6 also sharpens visual detail rendering compared to v2.5, with improved temporal consistency across scene cuts. This matters for multi-shot content where abrupt or inconsistent transitions degrade the viewing experience.
For developers building content generation pipelines (social media automation, creative brief to video, marketing content at scale), multi-shot storytelling and integrated audio remove two previously required pipeline stages: separate audio processing and manual scene composition.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Audio synthesis supports Chinese and English speech. If you need other languages, confirm support before you ship.
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Kling v2.6 Text-to-Video
Best for
- Narrative short-form content: A sequence of events or scenes in a single prompt for advertisements, educational clips, and social posts with story structure
- Marketing video generation: A text creative brief produces a complete audio-visual result without additional production steps
- Audio-visual content pipelines: Pipelines that require both visual and audio output from descriptive text at scale
- Concept prototyping: Rapid multi-scene video ideation before committing to production
Consider alternatives when
- Image-grounded visuals: A reference image must ground the visual appearance of the output, so use the i2v variant
- Silent speed priority: Generation speed and cost efficiency matter most and audio is not needed, so V2.5 Turbo t2v is faster and cheaper
- Fine-grained scene control: You need precise control over specific scene transitions or camera moves, so evaluate later Kling versions with structured scene control
Copy link to headingConclusion
Kling v2.6 Text-to-Video pairs multi-shot narrative output with native audio from one text prompt. One descriptive prompt can yield several scene cuts with sound in one pass. If your pipeline used to split silent video and audio work, v2.6 merges those steps.
Copy link to headingFrequently Asked Questions
What does multi-shot storytelling mean in Kling v2.6 Text-to-Video?
The model interprets a prompt describing sequential events and generates distinct scene cuts within the output, rather than a single continuous shot. A prompt structured as a brief narrative (scene A, then scene B) produces a video that transitions between those scenes.
How should I write prompts to take advantage of multi-shot storytelling?
Describe sequential events or scene changes within the prompt. For example, a prompt that describes an action followed by its result, or a product shown then used, tends to trigger multi-shot composition.
What audio types does Kling v2.6 Text-to-Video generate?
Natural speech in Chinese and English, action-synchronized sound effects, and environmental ambient audio. All produce in the same inference request as the video, with no separate TTS or SFX pipeline.
Can v2.6 t2v produce video without audio if audio is not needed?
Audio generation is built into v2.6. If you prefer silent video at lower cost, use v2.5 Turbo t2v instead.
How does v2.6 t2v differ from v2.5 Turbo t2v?
V2.6 adds native audio generation and multi-shot storytelling. V2.5 Turbo is faster and produces silent video. Choose v2.5 Turbo when speed and cost efficiency outweigh the need for audio or narrative scene structure.
What output durations and resolutions are available?
Outputs are available at five or 10 seconds, at up to 1080p resolution, in 16:9, 9:16, and 1:1 aspect ratios.