Deepgram is excited to announce the launch of our WebSocket API for our text-to-speech product, Aura. We've listened to users' pain points when building conversational AI agents with LLMs and TTS (text-to-speech).
With the WebSocket API, you can minimize latency by sending text tokens from any LLM as soon as they’re generated, reducing delays and creating a smoother experience. It also makes handling user interruptions easier and provides a simple way to estimate the number of concurrent conversations you can support, with one WebSocket per conversation.
To learn more, check out our getting started guide:
https://developers.deepgram.com/docs/streaming-text-to-speech