> For the complete documentation index, see [llms.txt](https://voicegenie.gitbook.io/voicegenie-ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://voicegenie.gitbook.io/voicegenie-ai/integrations/elevenlabs.md).

# ElevenLabs

**How can you generate keys in ElevenLabs ?**

Follow these steps to generate key in ElevenLabs 

* [x] Step 1: Log in to Elevenlabs
* [x] Step 2 : Click on <mark style="color:yellow;">My Workspace</mark> located in the bottom left corner and select <mark style="color:yellow;">API keys</mark>.
* [x] Step 3 : Click on <mark style="color:yellow;">Create Key</mark> and  enter a name for the key. Click on <mark style="color:yellow;">Create</mark>

<figure><img src="/files/f5SckjbD73HE5nInhObD" alt=""><figcaption></figcaption></figure>

* [x] Step 4 :Copy the generated API key.

**How can you  integrate ElevenLabs to VoiceGenie ?**

* [x] Step 1 : Log in to VoiceGenie  and navigate to integrations page .
* [x] Step 2: Click on <mark style="color:yellow;">ElevenLabs</mark>. Paste the copied API key into the appropriate field and click on <mark style="color:yellow;">Integrate</mark>.

<figure><img src="/files/JGnyq1Z92WddcjfuHkgt" alt=""><figcaption></figcaption></figure>

**Steps to use ElevenLabs voices in VoiceGenie :**

{% hint style="info" %}
Since the model is highly accurate, it will strive to clone everything present in the original samples with even greater precision than other models
{% endhint %}

* [x] Step 1: Go to the Assistant Customization section.
* [x] Step 2 : Select from the pre-made ElevenLabs voices or integrate your own generated voices.
* [x] Step 3 :  Select your desired accent .
* [x] Step 4 : To select the model you have following 3 options.&#x20;

- <mark style="color:yellow;">eleven\_turbo\_v2</mark> : A highly optimized model, specifically tailored for low-latency applications without sacrificing vocal performance.The accuracy is very good when using a properly created instant voice clone, and it is very stable.
- <mark style="color:yellow;">eleven\_turbo\_v2\_5</mark> : Turbo v2.5 generates human-like text to speech in 32 languages with low latency.We recommend Turbo v2.5 for users building real time, conversational interfaces in non-English languages.
- <mark style="color:yellow;">eleven\_multilingual\_v2</mark> : This model has good stability, great language diversity, and fantastic accuracy in cloning voices and accents.Its speed is rather remarkable.Since the model is highly accurate, it will strive to clone everything present in the original samples with even greater precision than other models

Choose any one model according to your requirements .

<figure><img src="/files/O6wrOmFQpB0W0vrJr16Y" alt=""><figcaption></figcaption></figure>

* [x] Step 5 : <mark style="color:yellow;">Save</mark> the changes to complete the integration.

:clap: **YAY !!! You have achieved ulta-realistic voice automation .**

<https://app.voicegenie.ai/>