noiseGPT is a product suite of creative audio generating tools powered by AI. We distinguish ourselves from others by having NO content policies, NO censorship and NO hidden built-in biases. AI as it should be.
noiseGPT stand for unrestricted AI generated voice-to-speech. It will have a plethora of use cases. It will start with memes. But soon you will see GPT being used for a wide range of applications. Think of user generated content, small studio movies, voice overs, animations, games, advertisements, audio books. The possibilities are endless. We will provide the user with an easy way to monetize their content.
Not only will we provide access to famous voices without any restrictions. Regarding the content. We will also allow users to train models on their own voice and thus free up their time when generating voice overs. People that contribute to the training of the models will be rewarded with tokens. Creatives and studios that want customized voices can either choose to do so themselves or make use of the nGPT community. Well-crafted combinations with other AI tools like content generation, video or image creation will mean companies and or individuals can create a massive amount of content without even lifting their pinky.
Early adoption within the crypto community means our models will be continuously updated and trained to be in line with the current trends. For example, most standard AI text to speech models will not be able to properly pronounce BNB or doge coin simply because these models were not trained on community generated sets nor got feedback from said community.
There a dozen ways to create audios with noiseGPT:
Discord Bot with OCR
noiseGPT OCR TTS
The noiseGPT Optical Character Recognition bot is a generative AI tool that reads out written texts in a photo and coverts it to an audio format in different voices. The bot is currently available in our discord server.
You can checkout cool video creations made with our OCR bot here.
You can specify a voice anywhere in your prompt. Currently available in the time of writing this documentation are:
Note that as we evolve, we will continue to add more voices