GPT4o does a hell of a job with audio narration, and really DESTROYS the whole business of ElvenLabs and other similar companies...
I had a feeling after watching the launch demos of GPT4o that you could use this new model for audio narration purposes, and forgo entire separate paid audio narration services like ElevenLabs. I have been very impressed with what ElevenLabs has provided up to now, with the money you pay being well worth their output, but why keep paying for a separate service with you have GPT4o? The video below is just the first test of my audio narration experiment using the new ChatGPT iOS app with voice features. It's a 5 minute narration of the intro and part of the first chapter story from my upcoming new book. This fictional story plays out in sections at the end of each chapter of the book as a fun hypothetical employment of the chapter content.
The audio stumbles a bit for some unknown reason around the one minute mark, but that's about the only negative to the whole result. I just had my phone about three inches away from my Yeti mic for recording purposes, and amplified the resulting audio file to make it easier to hear for playback. That's all I did to get the result you hear below. Honestly with the amount of complex wording and improvised non-standard terminology, I am frankly blown away with the quality result. You could easy divide up any narration tasks into 1000 word or less chunks and record them with any of the five voices that OpenAI offers, as well as you can tell the model to use any number of inflections and styles (see the OpenAI demo for multiple examples of this).
This is a FANTASTIC new tool for authors, but the end of multiple business that had a great run till OpenAI gobbled up their entire market overnight.
Link to Youtube Example video: https://youtu.be/0g5pb-1Enxk
