> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://developers.deepgram.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.deepgram.com/_mcp/server.

## Aura TTS Websocket Support

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](https://developers.deepgram.com/docs/streaming-text-to-speech)