> This is a page from the ElevenLabs documentation. For a complete page index, fetch https://elevenlabs.io/docs/llms.txt. For the full documentation in a single file, fetch https://elevenlabs.io/docs/llms-full.txt.

# What kind of voices can I create using Voice Design?

Voice Design can generate a wide range of voices, from realistic, human-like voices to more creative, character-style voices.

If you're unsure where to start, try a simple prompt like "middle-aged female newsreader." However, more detailed prompts typically produce more accurate and nuanced results.

You can include a variety of characteristics in your prompt, such as:

* age
* gender
* accent
* tone
* pacing
* emotion
* speaking style
* audio quality

Two additional controls help shape the output:

* **Loudness** adjusts the volume of both the preview and the saved voice.
* **Guidance scale** determines how closely the generated voice follows your prompt.

For more help crafting prompts, see our [Voice Design guide](/docs/product/voices/voice-lab/voice-design).

> ElevenLabs provides APIs and SDKs for text to speech, voice cloning, speech to text, sound effects, voice isolator, voice changer, and conversational AI agents. Build voice-enabled applications with lifelike audio generation.