> 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/mochi-sops/voice-clone-setup-guide.md).

# Voice Clone Setup Guide

#### Your setters send voice notes. Leads think they're hearing from you. Booking rates go up.

### Why It Works

Voice notes convert at 3–4x the rate of text in high-ticket DM sales. They feel personal, human, and immediate. The problem is you can't personally record hundreds of them at scale.\
Voice cloning solves this. Your setter types the message. Mochi generates it in your voice. The lead hears you.<br>

### What You'll Need

* An ElevenLabs account (Professional plan, \~$11/month)
* 60–90 minutes of clean recorded audio (90–120 min recommended)
* Your ElevenLabs API key and Voice ID
* 15 minutes to connect it in Mochi

### Step-by-Step Setup

#### Step 1 — Create Your ElevenLabs Account

Go to [elevenlabs.io](http://elevenlabs.io) → Sign up → Upgrade to Professional plan<br>

#### Step 2 — Record Your Voice Clone Audio

Recording tips:<br>

* Record in a quiet room — no background noise, no echo
* Use varied, expressive speech — not flat narration. Talk like you're having a real conversation with a lead one-on-one
* Vary your pace and tone — fast then slow, energetic then calm. ElevenLabs needs variation to clone properly
* Do NOT reuse course recordings — AI clones your "teaching voice" which sounds unnatural in DMs
* Aim for 90–120 minutes — more data = better clone
* Remove obvious stutters and long pauses before uploading

What to say: Talk naturally about your business, your clients, your day. Imagine you're leaving voice notes for 50 different leads — vary the energy, the context, the message length.<br>

#### Step 3 — Create Your Professional Voice Clone

* ElevenLabs → Voices → Create a Voice → Professional Voice Clone
* Upload your audio files
* Wait for processing (can take a few hours)
* ✅ Yellow tick = clone is ready

#### Step 4 — Get Your API Key

* ElevenLabs → Profile → Developers → API Keys → Create Key
* Enable: Text to Speech + Models
* Copy and save the key immediately (you won't see it again)

#### Step 5 — Get Your Voice ID

* ElevenLabs → Voices → My Voices → click your clone → Copy Voice ID
* Save this alongside your API key

#### Step 6 — Connect to Mochi

* Mochi → Settings → Organization → Voice Clone → Edit Voice
* Paste your API Key and Voice ID
* Save → should show "Voice Connected"
* Test it: type a message → click convert → listen → adjust stability/speed if needed

### Using Voice Notes in the Inbox

Once connected, your setters see a voice note button next to every message. They:<br>

1. Type the message as normal
2. Click the voice note button
3. Preview and approve
4. Hit send — it arrives as a native voice note in the lead's IG DMs

Add background sounds (ambient noise) to make it sound even more natural.<br>

### Troubleshooting

<br>

| <p>Issue<br></p>                       | <p>Fix<br></p>                                                                                                           |
| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
| <p>Voice sounds robotic<br></p>        | <p>Increase variety in your recording. Re-record with more natural speech. Adjust stability slider down in Mochi<br></p> |
| <p>Clone sounds too hyped<br></p>      | <p>You may have used course/teaching audio. Re-record in a conversational tone<br></p>                                   |
| <p>"Voice not connected" error<br></p> | <p>Check API key has Text to Speech + Models enabled. Re-paste both key and Voice ID<br></p>                             |
| <p>Poor audio quality in clone<br></p> | <p>Source recording had background noise. Re-record in a quieter environment<br></p>                                     |

***


---

# 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/mochi-sops/voice-clone-setup-guide.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.