Async makes it easy to create AI content directly from the Video Editor.
When you open the editor, the AI chat opens automatically and gives you different ways to start creating. You can use it to generate images, videos, audio, music, avatars, and voices, all in one place.
If you already know what you want to make, you can start with a prompt right away. If you want help choosing the right option first, click Explore models to browse what’s available.
What can you generate?
With AI chat, you can generate:
Images
Videos
Audio
Music
Avatars
Voices
This makes it easy to move from an idea to a finished asset without switching between different tools.
How to generate AI content
Open the Video Editor.
The AI chat will open automatically.
Enter a prompt describing what you want to generate.
Click Generate to create your content.
If you already have images or files uploaded, generated, or selected in the chat, you can use the @ symbol to tag a specific file and write your prompt around that exact item. You can also tag items directly from the timeline, including audio, image, and video files, but not subtitles or text. This helps the chat understand exactly which file or asset you want to work with.
You can also upload a photo or video. If you upload a video, it will first be added to your project. Once it appears on the timeline, you can select it and start working with it in the chat.
If you’re not sure where to begin, click Explore models first. From there, you can choose the type of content you want to create and browse the available options.
Explore models
Different models are designed for different types of creative work. Some may be better for speed, while others may be better suited for realism, readable text, cinematic video, audio generation, or maintaining a consistent character or subject across multiple assets.
When choosing a model, think about what matters most for your project. For example, you may want to look for an option that is best suited for:
Keeping the same character, spokesperson, or product consistent across multiple images
Creating images with clear, readable text
Generating cinematic or short-form video
Creating video and audio together
Producing realistic images or visuals
Generating music, voices, or other audio content
A simple way to choose is to start with the type of content you want to create, then try different options to see which result works best for your project.
Not sure where to start?
That’s okay. The easiest way to begin is by clicking Explore models and choosing the type of content you want to create.
From there, you can browse the available options and choose based on what matters most for your project. The AI chat can also suggest suitable models based on the type of content you’re planning to create.
💥Tips & Tricks💥
Start simple. Tell the chat in straightforward language what kind of content you want to create.
Add details step by step. If the first result isn’t quite right, refine your prompt with more direction around style, mood, setting, format, or subject.
Match the model to the task. Choose an option designed for the type of content and result you need.
Use Explore models when you’re unsure. It’s an easy way to understand the available options and find a good starting point.
Tag specific assets when needed. Use the @ symbol to make it clear which image, audio, or video file you want the chat to work with.
Experiment with your prompts. Small changes in wording or added detail can make a noticeable difference in the final result.