Kling Video O1
Neural Network
Kling Video O1 is a video generation model by Kuaishou: create videos from text descriptions and images.
Specifications
- Input
- text, images
- Output
- video
- Video duration
- 5–10 s
- Aspect ratio
- 16:9, 9:16, 1:1
Video generation
(duration 8 sec., 720p)
Video generation
(duration 8 sec., 1080p)
How it works Kling Video O1?
Kling Video O1 is a generative video model by Kuaishou that takes text and images as input and outputs video. This means both scenarios are available: text-to-video, where a clip is created from a text description, and image-to-video, where a ready-made frame or reference comes to life. The model is focused on cinematic results. Through BotHub, access to Kling Video O1 is available from Russia without a VPN or foreign card; payment is made with Russian cards in rubles and charged per generation, without a subscription. Other neural networks for text, images, and sound are available in the same window, allowing you to switch between them without new registrations. For product tasks, there is a unified API, and for companies, we offer contracts, invoices, and an admin panel with limits. Use cases are simple: advertising clips and product promos, vertical videos for social media, animation of photos and art, pre-visualization of scenes for music videos and short films, and dynamic inserts for presentations and training courses.Frequently asked questions about Kling Video O1
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
kling-video-o1 is a Kling video model that creates clips from text descriptions and animates uploaded images. It is suitable for advertising creatives, social media content, presentations, and animating static frames. In BotHub, the model is available from Russia without a VPN or foreign card, payment is made per use in rubles, and tokens do not expire.
Exact resolution, duration, aspect ratio, and file format are not specified in our data, so we cannot promise specific values. Two modes are confirmed: video generation from text and from images. It is more convenient to check the final output parameters in the BotHub interface when starting a task, where other video models are also available for comparison.
In our data, a separate reasoning mode for kling-video-o1 is not noted: it is a generative video model, not a text assistant for step-by-step reasoning. It processes the request immediately and outputs the result as a clip. If you need a tool that reasons before answering, check out the text models in BotHub — you can switch between them in one window.
Function calling and structured JSON output are not noted in our data for this model — it is designed for video generation, not for integration into software pipelines. For scenarios with function calling and JSON responses, BotHub's text models, available via a unified OpenAI-compatible API, are suitable.
Images — yes: the image-to-video mode is confirmed in the data, a clip can be created from a single frame or reference. Uploading audio and video as input is not noted, so we will not promise such a capability.
In our data, the model is marked as English-language, and support for Russian is not declared, so you should not expect stable understanding of Russian-language queries. If your task requires Russian, BotHub has text and video models with broader language support.