Skip to main content

Modalities

Depending on the modalities you want to implement, a different combination of models will be used. Select the modalities that match your agent's requirements.

Text Modalities​

Text to Text​

Standard conversational AI and text processing. Enables natural language understanding, generation, and conversation capabilities.

Text to Image​

Generate images from text descriptions. Create visual content based on textual prompts and descriptions.

Text to Voice​

Convert text to natural speech. Transform written content into spoken audio with natural-sounding voices.

Text to Video​

Generate videos from text prompts. Create video content based on textual descriptions and scripts.

Text to 3D​

Generate 3D models from text descriptions. Create three-dimensional objects and scenes from textual input.

Text to Music​

Generate music and audio from text prompts. Create musical compositions and audio content based on textual descriptions.

Image Modalities​

Image to Text​

Extract and understand text from images. Perform OCR (Optical Character Recognition) and image captioning to extract textual information from visual content.

Image to Image​

Transform and edit images. Modify, enhance, or transform images using AI-powered editing capabilities.

Image to Video​

Animate static images into videos. Convert still images into dynamic video content with motion and animation.

Audio Modalities​

Voice to Text​

Transcribe speech to text. Convert spoken audio into written text through speech recognition.

Voice to Voice​

Real-time voice conversation. Enable natural voice-to-voice interactions and conversations.

Video Modalities​

Video to Text​

Transcribe and analyze video content, extract captions and insights. Process video files to extract textual information, generate captions, and analyze content.