Customer engagement platform Twilio has announced a new collaboration with OpenAI, integrating the latter’s Realtime API into its customer engagement platform.
This integration with OpenAI will allow Twilio’s user base, which includes over 300,000 customers and more than 10 million developers, to create advanced conversational AI applications using OpenAI’s multilingual and multimodal GPT-4o model.
The Realtime API introduces streaming speech-to-speech (S2S) capabilities that aim to enhance the realism of AI voice interactions. This technology is designed to make conversations with virtual agents feel more human-like, addressing key elements such as pacing, tone, and interruption handling.
“Integrating OpenAI’s Realtime API with Twilio’s platform enables businesses to offer more natural, real-time AI voice interactions at scale,” said Inbal Shani, chief product officer, Twilio Communications. “Businesses can use this to create voice experiences that feel more human and can reduce operational costs and drive higher customer satisfaction.”
Developers are seen to benefit the most from a streamlined process, as they can now connect these advanced voice capabilities directly within Twilio’s platform, eliminating the need to coordinate multiple vendors. This allows for the efficient deployment of virtual agents within various workflows.
Twilio said it plans to enhance its platform further by addressing emerging risks associated with this technology, including deep fakes and voice-based prompt injections.