text to speech - Jeff Stivers

When I first wrote about AI text-to-speech tools in early 2023, the technology was moving quickly enough to feel experimental from month to month. The core idea was simple: instructional designers and training teams could write a script, generate narration, and produce audio without booking studio time, hiring voice talent, or recording multiple takes.

AI voice-over is no longer just a stand-alone audio capability. It is becoming part of a broader training media workflow. The same platforms now help generate scripts, record screens, create captions, translate content, produce avatars, edit video, and package content for delivery. The question is no longer whether AI text-to-speech is good enough for internal training. Often, it is. The better question is how training teams should use these tools without creating a messy, expensive production process.

The most important lesson may be this: fewer tools are often better.

Training teams have always been tempted by tool sprawl. One application for script writing. Another for voice-over. Another for screen recording, editing, animation, or captions. Each tool may be useful on its own, but the total workflow can become harder to manage than the content itself.

It’s remarkable how rapidly AI-powered text-to-speech technology has advanced over the past six months.

The current level of technology is so advanced that it can produce spoken words from a written script that sound almost natural, making it difficult for some listeners to discern the difference. Some high-end models can accurately generate speech in numerous languages, while also allowing for the manipulation of attributes such as intonation, inflection, intensity, and pauses. My Chinese colleagues have even confirmed the quality of a Chinese-language training video I produced using a text-to-speech tool that doesn’t support attribute management. Moreover, it’s possible to combine multiple languages seamlessly within a single script, transitioning from spoken Chinese to spoken English and back again.

These tools will be game-changing for training developers who produce content in multiple languages, as a single text-based script can be written in one language, translated into other languages, and then rendered by the AI text-to-speech tool. Below are two samples I produced from the same script, one in English and the other in Chinese. (Note – these videos were produced as tests. They have not been cleaned up for actual rollout to learners.)

English Language Version:

English Language Test

Chinese Language Version:

Chinese Version Test

In addition to examining the specific tool utilized to generate these examples, I have also explored several other tools, such as Amazon Poly, Speechify, Descript, and Google Cloud Text to Speech.

Category: text to speech

AI Text-to-Speech Tools Advance at Breakneck Speed, Enhancing Training Development