Superside Kling 3 Text-to-Video
Kling 3 Text-to-Video on fal. Returns a native VIDEO plus the URL, so SaveVideo or PreviewVideo connects straight in. Endpoints: pro - fal-ai/kling-video/v3/pro/text-to-video standard - fal-ai/kling-video/v3/standard/text-to-video 4k - fal-ai/kling-video/v3/4k/text-to-video turbo pro - fal-ai/kling-video/v3/turbo/pro/text-to-video turbo standard - fal-ai/kling-video/v3/turbo/standard/text-to-video fal price (2026-10-30): pro/text-to-video: For every second of video you generated, you will be charged $0.112 (audio off) or $0.168 (audio on), if voice control is used while generating audio you will be charged $0.196. For example, a 5s video with audio on and voice control will cost $0.98 | standard/text-to-video: For every second of video you generated, you will be charged $0.084 (audio off) or $0.126 (audio on), if voice control is used while generating audio you will be charged $0.154. For example, a 5s video with audio on and voice control will cost $0.77 | 4k/text-to-video: For every second of video you generated, you will be charged $0.42 regardless of whether audio is on or off. For example, a 5s video will cost $2.10. | turbo/pro: For every second of video you generate, you will be charged $0.14 . For example, a 5s video will cost $0.70. | turbo/standard: For every second of video you generate, you will be charged $0.112 . For example, a 5s video will cost $0.56.
- video
- video_url
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | pro | Which endpoint to call. These share one control surface and differ in quality, speed and price: pro - fal-ai/kling-video/v3/pro/text-to-video standard - fal-ai/kling-video/v3/standard/text-to-video 4k - fal-ai/kling-video/v3/4k/text-to-video turbo pro - fal-ai/kling-video/v3/turbo/pro/text-to-video turbo standard - fal-ai/kling-video/v3/turbo/standard/text-to-video |
| api_key | STRING | — | |
| promptopt | STRING | Text prompt for video generation. Either prompt or multi_prompt must be provided, but not both. | |
| multi_promptopt | STRING | List of prompts for multi-shot video generation. If provided, overrides the single prompt and divides the video into multiple shots with specified prompts and durations. JSON, as fal documents this field. | |
| generate_audioopt | BOOLEAN | true | 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. |
| cfg_scaleopt | FLOAT | 0.500–1 | The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt. |
| enable_safety_checkeropt | BOOLEAN | true | Disabling safety checks requires account authorization; unauthorized requests are always checked. |
| negative_promptopt | STRING | blur, distort, and low quality | — |
| durationopt | COMBO | 5 | The duration of the generated video in seconds |
| shot_typeopt | COMBO | customize | The type of multi-shot video generation. 'intelligent' lets the model automatically determine shot structure. |
| aspect_ratioopt | COMBO | 16:9 | The aspect ratio of the generated video frame |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| video | VIDEO | — |
| video_url | STRING | — |