Suno, a ChatGPT-Powered Chatbot, Can Generate AI Music Using Text Prompts

Mar18,2024



Listen is an artificial intelligence (AI) music generator that can create original songs using a simple text prompt. The AI ​​platform was first unveiled in July 2023 when it went into open beta and began adding users to its Discord channel to test models. Later, it also allowed users to generate AI music on its web interface. In December 2023, the platform collaborated with Microsoft to add an extension for Copilot, allowing users of the chatbot to create songs as well.

On Sunday, a report by the Rolling Stones highlighted the company's deeper workings and approach. According to the report, Suno creates original music based only on simple text prompts. Once the prompt is entered, the AI ​​model produces a 15-second long song within a minute. The platform has both free and paid tiers – Pro and Premier. Among the many upgrades, paid subscribers are also granted general commercial rights to the songs, while free account holders are prohibited from monetizing the songs. Currently, the cheaper Pro tier starts at $10 (roughly Rs. 830) per month.

At Gadgets 360 we tested Suno's web interface and found it to be user-friendly and easy to navigate. In just a few seconds, we were able to type our prompt and create original tracks that sounded extremely realistic. We used the prompt, “A loud pop song about an AI trapped inside a screen who is jealous of real humans,” and in less than a minute it created two versions of a song called 'Digital Envy.' The song generated can be heard here.

The report notes that music creation is done by Suno's native AI model; for lyrics and song titles, it uses OpenAI's ChatGPT. The US-based startup has not disclosed the architecture or any other details of its AI model. Privacy also gives rise to a paradox problem in that the source of the data on which it was trained is not known. This became an issue last year as the US music industry raised concerns with regulators over AI models training their copyrighted songs and then creating deepfake songs that sound identical to their voices.

However, Suno passes the difficult situation by not producing any music sung in the style of a real artist. If any such signal is recorded, it refuses to produce music. According to the report, the AI ​​startup is also in communication with major music labels. On February 23, Suno publicly Issued Its V3 Alpha model for Pro and Premiere users, which the company claims “creates more realistic, authentic music”. Only the V1 and V2 models are available to free users.


Affiliate links may be automatically generated – see our ethics statement for details.



Related Post

Leave a Reply

Your email address will not be published. Required fields are marked *