With VALL-E  you can create your own personalized audio files using just a 3-second recording of your voice and a written text prompt. 

Its new architecture outperforms older models because it doesn't need a lot of training data to make the speech sound natural.

Plus, it also preserves the same emotions and background sounds.

That's crazy.

3-second audio to whatever you want to do with your voice. 🪄

The use cases are endless:

• Read text messages from a sender in their own voice;

• Create personalized audiobooks with the author's voice

They have a few examples that you can try on their project page, but unfortunately, their code is not open-sourced yet.

📚 Educational corner

• How to make Gradio demo without coding using HuggingFace diffusers

• Open-source example on how you can build semantic search for any YT channel

• Create Chat-GPT like app using React and OpenAI

🛼 Makers corner

• arXiv Xplorer - semantic search engine for arXiv papers

• Create PRD's (Product Requirements Documents) with GPT3

• Free chatbot specialized in VC/startup knowledge

• A decision making tool powered by GPT3

• User experience AI assistant

🤓 Tech corner

• HyperReel: create a video that you can move around and look at from different angles

• RoDynRF - rendering 3D scenes in real-time from videos

• PACO: Detecting parts + attributes of common objects in a photo

🎨 Creativity corner

🧱 What are you building?

If you're using AI in your work or projects, I'd love to hear about it! Please reply to this email and let us know what you're up to. We may feature your work in our newsletter.

❤️ If you like The Prompt, and want to support my work:

• Share The Prompt with a friend, and invite them to subscribe here.

• Book an ad in The Prompt ( reply to this email if you’re interested)

Thank you for reading! ✌🏼