Tersa is an open-source platform designed for creating and visualizing AI workflows through an intuitive drag-and-drop interface. It allows users to seamlessly connect and run nodes, enabling the development of complex workflows powered by a wide range of industry-leading AI models. The tool integrates with 77 models from top AI providers, including OpenAI and Anthropic, offering capabilities such as text synthesis, image generation, video creation, speech transcription, and code transformation.
Tersa supports advanced text generation using models like GPT-4o and Claude 3.5 Sonnet, enabling users to synthesize answers by connecting text nodes for prompts and image nodes for attachments. It also facilitates image creation through models like DALL-E 3 and gpt-image-1, allowing users to generate visuals from text prompts or modify existing images. Additionally, it offers video production capabilities using models like Minimax's T2V-01-Director and Runway's Gen4 Turbo, with options to create videos from text prompts or transform images into video content.
For audio workflows, Tersa leverages models such as OpenAI's Whisper to transcribe speech, enabling seamless integration of text and audio nodes for enhanced interaction. Developers can also utilize AI-powered code analysis and refactoring, connecting code nodes for source files and text nodes for specifying transformation instructions.
With its user-friendly canvas and robust integration options, Tersa empowers users to build AI-driven solutions with ease and efficiency, making it a versatile tool for both technical and creative applications.
Pricing
Tersa offers three pricing tiers: Hobby (free) with 200 credits/month for personal use, Pro ($10/month) with 1600 credits/month and advanced features for small teams, and Enterprise (custom pricing) with unlimited credits and tailored solutions for large teams. Yearly plans save 20%.
