In September, OpenAI announced that ChatGPT, the popular generative artificial intelligence-based chatbot, was getting new capabilities added to it. These new capabilities were speech and image analysis, which allowed the chatbot to “see, hear, and speak”. This also allowed users to interact with the AI platform in a more intuitive way, and even have conversations, making it an entirely new interface. But what is the best way to use this feature? Let us take a look at these 5 ChatGPT use cases.
But before that, you should know this feature is only available to the paid users of ChatGPT. Further, while the chatbot cannot natively turn speech-to-text, which is required for you to have an actual conversation with it where both of you only use the speech medium, the company offers Whisper, its open-source speech recognition system, as a plugin to transcribe spoken words into text.
1. Accessibility use case
ChatGPT with its voice capability, can enable people with limited mobility or visual impairments to access information and services easily through voice interactions. Voice-enabled ChatGPT can assist with tasks like reading emails, dictating documents, and conducting online searches. So, if you receive a new email or a message, you can just ask it to read it for you and you can know the contents. You can also ask it to draft a reply and let it read it out to you, so you can easily respond.
2. Storytelling and language learning
One of the biggest benefits of an entirely voice-to-voice conversation is that you can use it for both learning and recreational purposes. It can be the perfect bedtime storyteller for kids who love to hear new stories every day before they sleep. Similarly, ChatGPT can be very helpful in case you’re learning a new language and want to practice it with someone. The chatbot with the Whisper plugin will ensure that you never run out of someone to talk to and improve your language learning.
The feature can significantly improve the cooking experience by providing audible step-by-step instructions, allowing users to focus on the task at hand without constantly referring to a written recipe. This feature is particularly beneficial for individuals with visual impairments or those who find it challenging to follow written instructions simultaneously with cooking. Additionally, the ability to listen to recipes hands-free promotes a more immersive and enjoyable cooking experience.
4. Live translation
Another great way to use this tool would be in translation. If you’re visiting a non-English speaking nation, or are talking to someone who does not speak your language, you can simply turn up ChatGPT and ask it to listen to the individual and translate what they’re saying.
5. Training and tutorials
For those who prefer verbal instructions for a task such as workouts, or a DIY project, this feature will be handy as they do not have to look at the steps over and over and instead can simply ask ChatGPT to guide them verbally.