Microsoft + Gutenberg colab: Thousands of free audiobooks

Project Gutenberg and Microsoft recently worked together to create thousands of free and open audiobooks using a new neural text-to-speech technology and Project Gutenberg’s public domain collection of e-books. Microsoft development team: “Our system allows users to customize an audiobook’s speaking speed and style, emotional intonation, and can even match a desired voice using a […]

Read More
Coding STEM

Powerful auto-transcription using AI (openAI’s Whisper)

Today, I’ll show you how to tap into the “world’s most powerful speech-to-text API” from our own applications. We’ll be using Deepgram, which is based on OpenAI’s Whisper AI SST technology. Deepgram claims to have trained their AI model with10,000+ years worth of audio data. (For more of my posts about Text to Speech and vice […]

Read More
Back To Top