--- title: "Text to Video SDK: AI Video Generation on Your Timeline" description: "Your users generate video clips from a prompt inside your video editor. Each clip lands on the timeline as regular footage, ready to trim, caption, and export." url: "https://img.ly/use-cases/ai-editor/text-to-video/" type: "page" --- > This is the markdown version of [Text to Video SDK: AI Video Generation on Your Timeline](https://img.ly/use-cases/ai-editor/text-to-video/). For all pages in one file, see [llms-full.txt](https://img.ly/llms-full.txt). For an index of all available pages, see [llms.txt](https://img.ly/llms.txt). --- # AI Editor: Generate the missing shot from a prompt, right on the timeline AI turns a written description into a short video clip, such as a vertical opener for social or a cutaway for an interview. The clip is generated inside your video editor and placed on the timeline. - Aspect ratio, length, and resolution per model - Sound with the clip on Veo models - A notification when the clip is ready **Available for:** - **Web:** [JavaScript](https://img.ly/docs/cesdk/js/user-interface/ai-integration/video-generation-b3122d.md), [React](https://img.ly/docs/cesdk/react/user-interface/ai-integration/video-generation-b3122d.md), [Angular](https://img.ly/docs/cesdk/angular/user-interface/ai-integration/video-generation-b3122d.md), [Vue.js](https://img.ly/docs/cesdk/vue/user-interface/ai-integration/video-generation-b3122d.md), [Svelte](https://img.ly/docs/cesdk/svelte/user-interface/ai-integration/video-generation-b3122d.md), [Next.js](https://img.ly/docs/cesdk/nextjs/user-interface/ai-integration/video-generation-b3122d.md) - **Desktop:** [Electron](https://img.ly/docs/cesdk/electron/user-interface/ai-integration/video-generation-b3122d.md) [Get in Touch](https://img.ly/forms/contact-sales.md) [Open the live editor demo](https://cdn.img.ly/demo/cesdk-web-examples/v1.84.0/examples/starterkit-ai-editor/index.html?demoPreview=true) ## A new shot without leaving the edit Clips from other AI tools need a download, an upload, and a crop. With text to video, your users generate them right on the timeline. ### Describe the shot Your users describe the action and the camera, like "a slow pan across a busy market at dusk". Then they pick an aspect ratio, a length, and a resolution the model offers. ### Keep editing while it renders The clip's place on the timeline is reserved while the model works, which can take a few minutes. A notification arrives when it's done, even with the panel closed. ### Work it into the cut Users trim, split, and caption the clip like uploaded footage, and it exports with the rest of the video. Trusted by **100+**\ industry leaders ---------------------- **Trusted by:** Digitas, Omneky, The Print Bar, Brandwatch, Planoly, HP, Shopify, Reuters, Hootsuite, Semrush, Shutterfly, one.com, Sprout Social, Constant Contact, Spread Group > "Integrating IMG.LY’s editor meant we didn’t have to build or maintain a complex editing layer ourselves. That kept our team focused on our core AI ad engine and saved us countless development hours — while still giving our customers the ability to polish and customize creatives at scale." -- Hikari Senju, CEO, Omneky > "With IMG.LY we built a central creative portal that now powers over 140 dealer campaigns across multiple automotive brands. Before this, asset creation was slow and inconsistent." -- Martin Röhr, Product Owner, Digitas > "By embedding IMG.LY’s editor we were able to hit key RFP requirements and deliver a template-based creative experience that now serves 1,000+ customers. It helped us win more deals and exceed enterprise expectations without needing to hire dedicated design teams." -- Rob Driscoll, Director of PM, Optimizely > "Since integrating IMG.LY’s editor, we now deliver 30,000+ ad creatives per month, dramatically shorten time-to-launch, and help our clients cut design spend by up to $10,000 per month." -- Logan Welbaum, Founder, Plai > "Our customers create over a million personalized postcards each year choosing from over hundreds of templates with IMG.LY’s SDK. It’s the only solution that allows us to build our own specialized, on-brand UI that integrates seamlessly with our platform." -- Jeanine Zaalberg, Product Manager, SwissPost > "From a developer’s perspective, the most powerful feature of the photo editor is the integration process. It was completely flawless, quick, and easy to integrate." -- Stefano Fornari, CTO, Funambol > "We compared IMG.LY SDK with other solutions and found that it would be the best fit for us since it provides all the features that are crucial for our use case." -- Carem Pereira, SCRUM Manager, HP [Reviews on G2](https://www.g2.com/products/img-ly/reviews) ## Choosing a text-to-video model The [AI Editor capabilities](https://img.ly/capabilities.md?solution=AI+Editor) list the video models currently supported, and [AI pricing](https://img.ly/ai-pricing.md) shows the average cost per generation on the [AI Gateway](https://img.ly/ai-gateway.md). ### Clip length Most models offer clips between 4 and 12 seconds. ### Aspect ratios Widescreen and vertical are standard, and some add square, 4:3, or 21:9. ### Resolution Up to 1080p, which decides how a clip holds up next to camera footage. ### Sound Veo models can generate the clip with its own sound. ## Set up text to video: models and formats ### Step 01: Connect video models Route them through the AI Gateway, which handles keys and billing in one place, or call a provider such as fal.ai through your own proxy. With several connected, users pick one per clip. ### Step 02: Preset your output formats Fix the aspect ratio and length to the formats your product ships, and rename or translate the panel's labels. ### Step 03: Keep earlier takes within reach Finished clips are kept in a per-model history inside the asset library, so an earlier take can go back into the edit without generating it again. ## Where teams use generated clips ### Social clips A creator generates a vertical clip, adds captions and music on the same timeline, and posts it. ### Ad openers A marketing team opens an ad with a generated shot, then cuts to real product footage. ### Missing B-roll An editor generates a cutaway to sit between two interview answers. ### Storyboards in motion A producer turns a written concept into rough moving shots to agree on pacing before anything is filmed. ## More AI features ### Image to Video Turn a generated or uploaded still into a short clip on the timeline. [Learn More](https://img.ly/use-cases/ai-editor/image-to-video.md) ### Text to Speech Turn a written script into a voiceover for the timeline. [Learn More](https://img.ly/use-cases/ai-editor/text-to-speech.md) ### Text to Sound Generate effects and ambience at the exact length a cut needs. [Learn More](https://img.ly/use-cases/ai-editor/text-to-sound.md) ### Text to Image Generate a new picture from a prompt, right on the canvas. [Learn More](https://img.ly/use-cases/ai-editor/text-to-image.md) ## Get in touch: Generate a clip in the AI Editor demo Switch to video mode, describe a shot, and watch it arrive on the timeline. Then talk to us about adding text to video to your product. [Talk to Our Team](https://img.ly/forms/contact-sales.md) [Open Demo](https://img.ly/demos/ai-editor.md) ## Frequently Asked Questions ### General **Q: What is text to video?** A: Text to video is generative AI that creates a short video clip from a written description, including motion and camera movement. In CE.SDK, it runs inside the video editor, and the result is a regular clip on the timeline. **Q: How long does a clip take to generate?** A: Up to a few minutes, depending on the model and the clip. Users can close the panel and keep editing in the meantime. **Q: Which video models are supported?** A: Any video model on the Gateway, or models from fal.ai, Runware, EachLabs, and ByteDance called through a proxy you host. **Q: Can the model improve the prompt?** A: Some can rework the description before generating, such as Veo 3.1 with its prompt enhancement and MiniMax with its prompt optimizer. **Q: How is video generation billed?** A: Depending on the model, per second of output or per finished video. Teams pay the provider directly or through the Gateway, and the plugin itself comes with your CE.SDK license. --- ## More Resources - **[IMG.LY Website](https://img.ly/index.md)** - Creative editing SDKs for photo, video, and design - **[Documentation](https://img.ly/docs/cesdk/)** - CE.SDK developer documentation - **[Contact Sales](https://img.ly/forms/contact-sales.md)** - Get a custom quote. A public JSON API accepts the request directly, no account or key needed. Ask your user for consent and their details first.