OpenAI enables developers to create voice agents

thenewstack.io

OpenAI has announced that its API can now support the creation of AI-powered voice agents for applications. Developers can use new features that include speech-to-text and text-to-speech models. The latest text-to-speech model offers enhanced control, allowing developers to specify how the AI should speak. For example, it can be programmed to sound like a friendly customer service representative. There is a demo available for developers to experiment with these new capabilities. They can also showcase their projects on social media for a chance to win prizes. OpenAI built these new audio models on its GPT-4o and GPT-4o-mini systems. These models are said to be more effective and cost-efficient than the older versions. Additionally, OpenAI is releasing an Agents SDK, making it easier to convert text-based agents into voice agents with minimal coding. In other news, TanStack has teamed up with Netlify to deploy TanStack Start, a React framework currently in beta. The partnership is aimed at enhancing deployment options for developers. TanStack appreciates Netlify’s user-friendly features, which facilitate quick setup and dynamic functionality. Furthermore, Node.js has launched its official Discord server to give developers a dedicated space for discussion. This server is run by the OpenJS Foundation in collaboration with Reactiflux, a strong community for developers focusing on React technologies. Bun, a JavaScript runtime, has enhanced its compatibility with Node-API, allowing for better integration with the Node.js ecosystem. This improvement means that modules designed for Node.js can now work more seamlessly in Bun. The most recent version of Bun passed nearly all of Node's compatibility tests. Lastly, a survey found that many gamers frequently encounter bots in online games. It revealed that 59% of players reported seeing unauthorized bots, and a large majority believe these bots negatively affect gameplay. In response to these findings, the blockchain initiative World Network is collaborating with Razer to promote a fairer gaming experience by introducing a secure ID verification system for human players.


With a significance score of 2.8, this news ranks in the top 26% of today's 18173 analyzed articles.

Get summaries of news with significance over 5.5 (usually ~10 stories per week). Read by 9000 minimalists.


loading...