You can now upload images and ask the AI any questions about them. This includes generating social media captions, analyzing screenshots, and interpreting photos.
It has 200,000 context window and 2x Decrease in Hallucination Rates.
Now you can instantly clone your voice using AI and generate text-to-speech audios that sound just like you.
We upgraded our AI Transcription to produce amazing content for you 10x faster. Just upload your audio or video file and get a summary, social media posts, article, newsletter and many more.
GPT-4 Turbo, the latest GPT-4 model is now available on Easy-Peasy AI. It has 128k context window. Trained with data up to April 2023 and has the access to the latest data via web browsing.
We've added 3 new models to our Image Generator: DALL-E 3, Stable Diffusion XL, Kandinsky. The most advanced model, DALL-E 3 is proficient in rendering complex features like text, hands, and faces with remarkable accuracy.
Whether for work, personal or research, custom instructions let you define the ideal AI responses.
For programming: 'Assume I'm using Next.js, Typescript, Tailwind and Supabase.'
For professional emails: 'I'm a CMO at a Singapore AI startup. Use formal business language.'
With custom instructions you can:
- ✅ Specify professional background
- ✅ Outline preferred libraries/frameworks
- ✅ Set preferred tone and language
- ✅ Provide contextual information
This allows the AI to generate more tailored, relevant responses for your unique use case. No more one-size-fits-all!
To add custom instructions, simply add them on the Brand Voice page. You can define multiple instruction sets and easily switch between them.
Now you can record audio through your microphone and have it instantly transcribed. The text can then be used to generate summaries, descriptions, posts, articles and threads!
Trained on multiple languages, it's robust & accurate, delivering near-human speech synthesis. Languages we support: 🇬🇧🇨🇳🇪🇸🇮🇳🇵🇹🇫🇷🇩🇪🇯🇵🇸🇦🇰🇷🇮🇩🇮🇹🇳🇱🇹🇷🇵🇱🇸🇪🇵🇭🇲🇾🇷🇴🇺🇦🇬🇷🇨🇿🇩🇰🇫🇮🇧🇬🇭🇷🇸🇰🇮🇳
Just paste the URL to get an automated transcription in seconds. Harness the power of AI to convert speech to text!
📢 Exciting news! We're thrilled to announce that GPT-4 32K and Claude 2 are now available on our platform! 🎉 Dive in and explore the cutting-edge capabilities of this revolutionary AI model with a more extended context window.
Choose from predefined personas or create your own. Whether you need a friendly advisor, a diligent assistant, or an imaginative storyteller, we've got you covered! The best part? Our AI can generate persona instructions just for you!
'Grammar Corrector' and 'Write Like a Native Speaker' templates now display the differences between the original and corrected text.
We trained Marky to let you upload documents and ask any question you'd like. For example, watch the video below where we upload two different files: Apple's (in PDF) & Microsoft's (in Docx) SEC reports and chat with them. AI analyzes uploaded documents & provides answers in a snap!
Now the transcription and summary are much more correct and clean.
Now you can enjoy enhanced image quality in all your creations, along with the ability to choose the number of image variants to generate for even more artistic possibilities. We've also increased the default image size from 512x512 to a stunning 1024x1024, ensuring your images look their best. Plus, we've included additional image size options for maximum flexibility.
We're thrilled to announce that Chat with Marky is now powered by the incredible GPT-4! 🚀. What does this mean for you? Expect faster, smarter, and more engaging conversations than ever before!