What is multimodal AI?

Multimodal AI is a model or system that works with more than one kind of data, such as text, images, audio and video, in its input, its output or both.

Early language models only read and wrote text. Modern models can look at images and documents, listen to audio and, in some cases, generate images or speech directly.

Often a product is multimodal because it combines several specialised models: an LLM for text, an image model, a video model, a text-to-speech model and a speech-to-text model.

For users the result is one place to describe a picture, read a scanned contract, transcribe a meeting or turn a script into a voiceover.

Multimodal AI in Aikeedo

Aikeedo combines chat, image, video, voiceover, transcription and document reading in one platform, each with its own choice of models and credit rates.

• All Aikeedo apps
• AI models