The Dynamic Prompt Box in Artlist’s AI Toolkit is designed to adapt to the type of content you want to generate, whether it’s video, images, voiceovers, or music. Each content type and model unlocks different capabilities and input options, helping you create more precise and customized results.
Accessing the AI Toolkit
- From the top panel on the Homepage, click AI Toolkit.
- At the bottom of the prompt field, open the dropdown menu.
- Select the content type
- Video
- Image
- Voiceover
- Music
Once selected, the prompt box and available tools will automatically update based on your chosen content type and model.
Selecting a model
The Model Picker helps you quickly find the most suitable AI model for your creative or production needs when generating videos, images, and voiceovers.
Instead of browsing all available models, you can narrow down results using filters tailored to your workflow, preferences, and technical requirements.
You can apply a single filter or combine multiple filters to refine your results with greater precision.
To choose a model:
- Select your desired filters.
- Browse the available models.
- Click Use Model once you’ve found the best fit.
Video
Video models can be filtered by the following categories:
Models
Filter models by AI brand:
- xAI
- Happy Horse
- Minimax
- Kling
- Lightricks
- Bytedance
- Open AI
- Wan
- Veed.io
- HeyGen
- Sync Labs
- ElevenLabs
Features
- Audio generation
- Avatar
- Dubbing
- Lipsync
- Motion control
- Multishots
- Mutli-type references
- Negative prompt
- Start / End frame
- Video editing
- Video extension
Best for
- Cost-effective
- Fast generations
Images
Image models include the following filters:
Models
Filter models by AI brand:
- Artlist Original
- Flux
- Open AI
- xAI
- Hunyuan
- Ideogram
- Imagen
- ImagineArt
- Kling
- Bytedance
- Wan
- Z-Image
Best for
- Cost-effective
- Fast Generation
Voiceover
Voiceover models can be filtered using:
Models
Filter models by AI brand:
- Cartesia
- ElevenLabs
- Minimax
Features
- Custom Voice
- Speech-to-Speech
- Speed Control
- Text-to-Speech
Using the Plus (+) Menu
Click the Plus (+) icon inside the prompt box to access additional input options.
Note: The available actions depend on the selected model. Not all options appear in every mode.
Video
When generating video, you can guide the AI with multiple reference types:
- Image Reference
Upload an image to influence the visual style, composition, or subject. - Video Reference
Provide a clip to guide motion, pacing, or cinematography. - Audio Reference
Add sound to influence rhythm, tone, or syncing. - Start & End Frame
Define how your video begins and ends for more controlled transitions.
💡Pro Tip: Combining references (e.g., image + audio) can significantly improve results
Image
For image generation, you can refine outputs with:
- Image Reference
Upload a visual to edit or guide style, colors, or structure.
Voiceover
Create realistic voice content using:
- Speech to Speech
Upload a voice recording to transform or enhance it using AI. - Custom Voice
Generate a unique AI voice tailored to your project.
Music
Enhance music generation with:
- Image Reference
Upload an image to influence the mood, tone, or atmosphere of the track.