> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.resemble.ai/guides/prompt-generation/getting-started/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.resemble.ai/_mcp/server.

# Getting Started

Use the `prompt` attribute on the SSML `<speak>` tag to change delivery without creating a new voice. Prompts let you steer style, emotion, and context dynamically at synthesis time.

## What Prompts Can Do

* Shift speaking style (casual, formal, storyteller)
* Set emotion (excited, calm, sympathetic)
* Provide context (news reader, sports announcer, meditation guide)
* Personalize delivery for each request while reusing the same `voice_uuid`

## How It Works

```xml
<speak prompt="Speak this like an excited sports announcer">
  The home team just scored the winning goal in the final seconds!
</speak>
```

The prompt text guides the synthesis model just before it renders the clip. Combine prompts with other SSML features such as inline tags (`[pause]`, `[laugh]`) or wrapping tags (`<whisper>`, `<slow>`) for fine-grained control.

### More Prompt Examples

```xml
<speak prompt="Speak in a calm, soothing voice">
  Welcome to your guided meditation session. Let's begin by taking a deep breath.
</speak>
```

```xml
<speak prompt="You are a knowledgeable science educator explaining complex concepts in an engaging way">
  Black holes form when massive stars collapse at the end of their life cycle.
</speak>
```

```xml
<speak prompt="Speak with excitement and enthusiasm, like you're sharing amazing news">
  We've just received confirmation that our project has been approved with full funding!
</speak>
```

### Best Practices

* Keep prompts concise and descriptive.
* Use natural language as if you were coaching a voice actor.
* Experiment—minor wording tweaks can produce noticeably different results.

Continue to [Generate Audio](./generate-audio) for a full example request.