OpenAI Releases RealtimeAPI for Speech Synthesis in Third-Party Apps

TapTechNews October 2nd news, the tech media TheDecoder published a blog post yesterday (October 1st), reporting that OpenAI released the RealtimeAPI at the San Francisco Developer Conference (DevDay), which allows developers to integrate speech synthesis technology in third-party applications by calling this API.

OpenAI stated that by calling the new RealtimeAPI, developers can add 6 kinds of AI voices in their applications. TapTechNews note: For OpenAI to avoid legal issues, developers cannot use third-party voices.

OpenAI also demonstrated other application scenarios, stating that it can be used for customer support, language learning, educational software, etc. Developers can enhance the user experience by using voice interaction:

OpenAI demonstrated a travel planning application made by calling the RealtimeAPI at the launch event. Users can talk to the AI assistant about the trip to London and get quick responses. This API can also add restaurant suggestions on the map.

Speak is a language learning application that uses the RealtimeAPI to support its role-playing function and encourages users to practice conversations in new languages.

Healthify is a nutrition and fitness guidance application that uses the RealtimeAPI to achieve a natural conversation with its AI coach Ria, while involving human dietitians when personalized support is needed.