> For the complete documentation index, see [llms.txt](https://themochi-app.gitbook.io/mochi-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://themochi-app.gitbook.io/mochi-docs/feature-and-settings/voice-clone.md).

# Voice Clone

Let your setters send voice notes that sound like you. Leads think they're hearing from you personally — without you recording anything.

## Why Voice Notes Matter

Voice notes get 3-4x higher response rates than text. But recording individual messages doesn't scale. With voice cloning, your setter types the message, and Mochi generates audio in your voice. The lead hears you. Your setter handles the volume.

## Setup

Voice cloning uses ElevenLabs. Here's how to set it up:

{% stepper %}
{% step %}

### Create an ElevenLabs Account

Go to [elevenlabs.io](https://elevenlabs.io/) and create an account.
{% endstep %}

{% step %}

### Create Your Professional Voice Clone (PVC)

Create a **Professional Voice Clone (PVC)** in ElevenLabs. This is a high-fidelity clone trained on your voice samples — it sounds significantly more natural than the default Instant Voice Clone.

Follow ElevenLabs' official PVC guide for full instructions: [Professional Voice Clone Guide](https://elevenlabs.io/docs/voices/voice-lab/professional-voice-cloning)
{% endstep %}

{% step %}

### Get Your API Key

1. In ElevenLabs, go to **Developers → API Keys**
2. Create a new key
3. Enable **Text to Speech** and **Models** permissions
   {% endstep %}

{% step %}

### Get Your Voice ID

1. In ElevenLabs, go to **Voices → My Voices**
2. Copy your Voice ID
   {% endstep %}

{% step %}

### Connect to Mochi

1. In Mochi, go to **Settings → Organization → Voice Clone**
2. Enter your ElevenLabs API key
3. Enter your Voice ID
4. Choose your preferred voice model and playback rate
5. Save
   {% endstep %}
   {% endstepper %}

## Using Voice Notes

Once configured, your team can send voice notes from the Inbox:

1. Open a conversation
2. Type the message you want to send as audio
3. Click the voice note option
4. Mochi generates the audio in your voice and sends it as an Instagram voice note

The lead receives it as a normal voice message in their DMs.


---

# 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, and the optional `goal` query parameter:

```
GET https://themochi-app.gitbook.io/mochi-docs/feature-and-settings/voice-clone.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.