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

# Text-to-Speech Streaming

Deepgram's Text-to-Speech WebSocket interface provides a real-time, interactive solution for converting streaming text to speech. This API is ideal for applications that require immediate audio feedback and continuous data streams, such as live customer service chatbots and interactive voice response (IVR) systems. By leveraging WebSocket technology, our API ensures low-latency communication and efficient handling of concurrent connections, delivering a seamless and responsive user experience.

## Getting Started with WebSockets

To begin using Deepgram's Text-to-Speech WebSocket interface, there are several pages that provide information on getting started. For further assistance, please refer to the following pages:

* [Getting Started](/docs/streaming-text-to-speech)
* [Feature Overview](/docs/tts-streaming-feature-overview)
* [API Reference](/reference/text-to-speech/speak-streaming)

> An introduction to using Deepgram's Aura Text-to-Speech API to convert streaming text into audio using WebSockets.

## Docs

- [Getting Started](https://developers.deepgram.com/docs/streaming-text-to-speech.md): An introduction to using Deepgram's Aura Streaming Text-to-Speech Websocket API to convert streaming text into audio.
- [Feature Overview](https://developers.deepgram.com/docs/tts-streaming-feature-overview.md): Below is a matrix of Deepgram's Aura streaming text-to-speech Websocket API features. Please refer to the corresponding documentation for more details.
- [Template Apps](https://developers.deepgram.com/docs/tts-streaming-template-apps.md): Get up and running fast with our Aura (/v1/speak) streaming text-to-speech template applications, fully integrated with Deepgram out-of-the-box.
- [Flush](https://developers.deepgram.com/docs/tts-ws-flush.md): Flush forces the generation of audio from Deepgram's internal text buffer.
- [Clear](https://developers.deepgram.com/docs/tts-ws-clear.md): Clear will clear out Deepgram's internal text buffer.
- [Close](https://developers.deepgram.com/docs/tts-ws-close.md): Close will close the websocket connection immediately.