> 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.

# Feature Overview

> **Info**
>
> To learn how to get up and running with Text-to-Text Intelligence, read the [Text Intelligence](/docs/text-intelligence) getting started guide.

## Text To Text Intelligence features

| Feature                                                | Pre-recorded? | Streaming? | Language(s)                                                        |
| ------------------------------------------------------ | ------------- | ---------- | ------------------------------------------------------------------ |
| [Sentiment Analysis](/docs/text-sentiment-analysis)    | Yes           | No         | [English (all available regions)](/docs/models-languages-overview) |
| [Intent Recognition](/docs/text-intention-recognition) | Yes           | No         | [English (all available regions)](/docs/models-languages-overview) |
| [Topic Detection](/docs/text-topic-detection)          | Yes           | No         | [English (all available regions)](/docs/models-languages-overview) |
| [Summarization](/docs/text-summarization)              | Yes           | No         | [English (all available regions)](/docs/models-languages-overview) |

## Rate Limits

> **Info**
>
> For information on Deepgram's Concurrency Rate Limits, refer to our [API Rate Limits Documentation](/reference/api-rate-limits).

## Deepgram Self-Hosted

> **Info**
>
> Having challenges with performance and latency? Check out Deepgram's [Self-Hosted Solution](/docs/self-hosted-introduction) to get the benefits of running your own hosted instance of Deepgram.