Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore how to create a synthesized version of your own voice using Azure Custom Neural Voice in this conference talk from NDC London. Learn the basics of training and fine-tuning a voice model with minimal code, enabling you to convert text into natural-sounding speech for various applications such as telephony, voice-overs, or even attending meetings on your behalf. Discover techniques for enhancing your model's training data, including using widely available tools and APIs to identify individual speakers and transcribe technical language from larger audio sources like podcasts. Gain the knowledge and inspiration to experiment with "cloning" your voice, opening up new possibilities for personal and professional use.