> For the complete documentation index, see [llms.txt](https://docs.convai.com/api-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/other-integrations/third-party-api-integrations/elevenlabs-api-integration.md).

# ElevenLabs API 集成

{% hint style="danger" %}
**目前，由于 44.1kHz 音频输出，仅 ElevenLabs 账户及其对应的 Pro 及更高级套餐兼容。**\
\
**所有等级的 Convai 账户都可以添加 ElevenLabs API 密钥集成。**
{% endhint %}

{% hint style="info" %}
**注意：如果你在与角色对话时收到 token 错误，请确认你的 ElevenLabs 订阅有效，并且你的账户上还有剩余的 token 配额。** [**ElevenLabs.io**](https://elevenlabs.io/) **仪表板。**
{% endhint %}

步骤 1. 前往 [elevenlabs.io](https://elevenlabs.io/) 然后进入你的个人资料部分

<figure><img src="/files/9660d2f7ac14700be890f4b02a9b0b77da8a4faf" alt=""><figcaption></figcaption></figure>

步骤 2. 在个人资料部分，使用以下权限创建一个 API 密钥：

`文本转语音` : `访问`

<figure><img src="/files/e46d5f47cfbf1d4b683d19a5f9dc44e4689e7cbf" alt=""><figcaption></figcaption></figure>

`声音` : `读取`

<figure><img src="/files/98533a01b6cbf61f8d14a0611f91ff3a16b6e88a" alt=""><figcaption></figcaption></figure>

`用户` : `读取`

<figure><img src="/files/ef9e5a3d322bebe19714664f0aa5bd67b2981a99" alt=""><figcaption></figcaption></figure>

然后复制 API 密钥以进行下一步。

步骤 3. 接下来，登录 convai.com 并打开你的个人资料页面

<figure><img src="https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FtvHXv9Cpl8QzA5tY9MJh%2Fuploads%2FAJxT96IvZIPOhEMg3M5G%2FScreenshot%202024-02-06%20at%206.45.04%E2%80%AFPM.png?alt=media&#x26;token=9103ac42-6597-48d8-8e0f-c429acfaaa49" alt=""><figcaption></figcaption></figure>

步骤 4. 在右下角的“API 集成”中，点击“添加新密钥”按钮

<figure><img src="/files/54da6b585219920848cf90aee3825f95f898afef" alt=""><figcaption></figcaption></figure>

步骤 5. 随后会弹出一个窗口，选择 ElevenLabs，然后粘贴你的 API 密钥并点击“添加”。

{% hint style="danger" %}
**你的声音在 Convai 仪表板中显示出来需要一些时间（约 12 小时）。**\
**你可以通过删除并重新添加 ElevenLabs API 密钥来加快查看新添加声音的过程。**
{% endhint %}

<figure><img src="https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FtvHXv9Cpl8QzA5tY9MJh%2Fuploads%2Fs8EbPIU1l9PpKRJNuseC%2FScreenshot%202024-02-06%20at%206.48.43%E2%80%AFPM.png?alt=media&#x26;token=774991bb-c41a-4743-afed-6e0094850c81" alt=""><figcaption></figcaption></figure>

步骤 6. 前往任意角色，在其角色描述下选择角色的声音，向下滚动到底部，你会看到一个新部分“Elevenlabs-Private-Voices”，你的所有声音都会显示在那里。按需选择并使用。

<figure><img src="https://files.gitbook.com/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FtvHXv9Cpl8QzA5tY9MJh%2Fuploads%2FS9INCC48hKOpkP85fLXI%2FScreenshot%202024-02-06%20at%207.04.09%E2%80%AFPM.png?alt=media&#x26;token=f0168791-2e67-49fe-bc8b-21eee468870b" alt=""><figcaption></figcaption></figure>


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.convai.com/api-docs/zh/cha-jian-yu-ji-cheng/other-integrations/third-party-api-integrations/elevenlabs-api-integration.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.