Tired of generic meditations? Explore how ChatGPT crafts personalized scripts based on your name, mood, and happy place. Does AI unlock a deeper path to relaxation? Find out!
Highlights
- Who Is Josh Sackman?
- Introduction and Initial Exploration
- Training ChatGPT and Incorporating Inputs
- Selecting a Text-to-Speech Tool and Initial Observations
- Adjusting Voice Parameters and Finalizing the Script
- Trust in ChatGPT and the Quality of AI Voices
- Personalized Meditation Potential and Final Thoughts
Who Is Josh Sackman?
Josh Sackman is the President and Co-founder of AppliedVR, as well as an advisor and board member specializing in digital health innovation. His LinkedIn profile showcases his extensive experience in leading and advising healthcare technology companies, with a particular focus on creating immersive virtual reality solutions to improve patient outcomes. Moreover, Josh is recognized for his significant contributions to digital health and his exceptional ability to drive innovation in therapeutic virtual reality applications.
In this article, Josh Sackman shares his exploration of how AI can help create personalized meditations.
Introduction and Initial Exploration
Building on the exciting news that OpenAI has released APIs for ChatGPT and Whisper. Now, developers can integrate these powerful models into their applications. This development prompted me to explore the potential uses of these services.
In my previous article, “ChatGPT Is My Meditation Teacher,” I discussed the possibility of using generative AI scripts to personalize meditation experiences. Taking that concept a step further, I’ve spent this week simulating a ChatGPT-powered meditation app.
Training ChatGPT and Incorporating Inputs
To start, I trained ChatGPT on parameters for designing meditation experiences and provided examples of meditation scripts. I asked it to incorporate three input variables: Name, Mood, and Happy Place.
At first request, it only incorporated two of the three. Upon a second request, it captured the three inputs and integrated them into the meditation script nicely.
Selecting a Text-to-Speech Tool and Initial Observations
To bring this to life, the next step was finding an AI text-to-speech tool that would provide a natural, relaxing voice to guide this meditation. There were a number of tools I tried. All had seemingly different benefits and limitations, and I landed on Murf.ai.
Murf had a wide selection of different voices, and the interface made it easy to edit the script and incorporate different elements into the production such as background music and images/video.
Adjusting Voice Parameters and Finalizing the Script
One big first observation is that to capture the essence of meditation, the speed of the voice, the pacing, and the incorporation of pauses in the script are really important. However, by default, voice-to-text does not factor those elements into the reading. In fact, it does not sound like a meditation. It sounds like a pharmaceutical commercial where they are reading the side effects of a drug. So I needed to adjust the voice speed and manually incorporate pauses within the syntax. It still doesn’t sound as perfect and polished as a trained human, but it’s certainly closer. I finalized it by incorporating a Dall-E image of a “Big Sur Sunrise” as the thumbnail.
Trust in ChatGPT and the Quality of AI Voices
After conducting the experiments, here are my takeaways:
- I still have a tough time trusting ChatGPT. Trust in ChatGPT requires a quality review of outputs. ChatGPT requires a quality review of outputs, so I’m not sure I’d fully trust an unsupervised output to return in an application based on the API. Whether it’s ChatGPT ignoring some of the input parameters or potentially incorporating bias into the response, I’d be concerned having fully generative output without the opportunity to do some quality control first.
- AI Voices Don’t Quite Sound Human. Text-to-audio sounds really close, but the technology has a way to go to create a truly naturalistic output. While the voices sound pretty solid, the tone of voice, pacing, and emotion don’t quite come through in the delivery compared to a voice actor.
- Personalized Meditation On-Demand Is Quite Possible. Limitations aside, AI can generate meditation audio in moments. It means, this audio can even weave in personal details, deepening your connection to meditation. I really enjoy the concept of incorporating personal details into a meditation, and being able to customize certain variables such as voice and music.
Personalized Meditation Potential and Final Thoughts
Personalized Meditation On-Demand Is Quite Possible. Even with the limitations mentioned, it’s amazing how quickly a meditation audio can be generated. This audio can even incorporate personal details, helping users connect deeply to their meditation practice.I really enjoy the concept of incorporating personal details into a meditation and being able to customize certain variables such as voice and music.
What would your custom meditation look like?
The original article can be found here.
Highlights
- Who Is Josh Sackman?
- Introduction and Initial Exploration
- Training ChatGPT and Incorporating Inputs
- Selecting a Text-to-Speech Tool and Initial Observations
- Adjusting Voice Parameters and Finalizing the Script
- Trust in ChatGPT and the Quality of AI Voices
- Personalized Meditation Potential and Final Thoughts
