# Voices

> Create a voice for speech generation by describing it or cloning it from recordings, share it with your workspace, and use it in canvas, chat and MCP.

Source: https://endless.app/docs/settings/voices

**Settings → Workspace → Voices** holds the voices used for speech generation. It lists
**Workspace voices** (yours and those teammates shared, badged **Described** or **Cloned**,
**Shared** or **Private**) and **Endless voices**, which every workspace can use and no one can
edit.

## Create a voice

Press **"Create voice"**. You need permission to create content, so a Viewer or Billing
manager can use shared voices but not create them.

| Method                           | How it works                                            | Voice slot |
| -------------------------------- | ------------------------------------------------------- | ---------- |
| **Create by prompting**          | Designed from a written description, in under a minute. | No         |
| **Create from audio references** | Cloned from one person's recordings, in about a minute. | Yes        |

### By prompting

<Steps>
  <Step>
    ### Describe it

    In &#x2A;*"What it sounds like"**, describe age, accent, tone and pace in at least 20 characters.
    English works best.
  </Step>

  <Step>
    ### Name and share

    Enter a **Name*&#x2A;. Turn on &#x2A;*"Share with the workspace"** so teammates can use it; otherwise only
    you see it.
  </Step>

  <Step>
    ### Press "Create voice"

    If the description doesn't work, the error shows while the form is still open.
  </Step>
</Steps>

A described voice costs a few extra credits each time it speaks, because its sample is
generated again.

### From recordings

1. Add **Recordings** of one person speaking, without music or background noise. 1 to 2
   minutes in total works best. Only recordings you uploaded or generated yourself can be used.
2. Pick the **Provider**. The voice works with that provider's speech models.
3. Enter a **Name** and choose whether to share it.
4. Tick the consent box confirming the person agreed to have their voice cloned.

<Callout type="warn">
  A workspace can hold **three cloned voices**, counting every cloned voice
  whoever made it and whether it's shared. At the limit, delete one or create a
  described voice instead.
</Callout>

## Share or delete a voice

Only the voice's creator sees its menu: &#x2A;*"Share with the workspace"*&#x2A; or &#x2A;*"Make private"*&#x2A;, and
&#x2A;*"Delete voice"**. Deleting removes it for everyone. Audio it made and the recordings it was
cloned from stay. If you move a training recording to the [trash](/docs/settings/trash), the voice
stays, but it can't be retrained from that recording once the trash is emptied.

## Use a voice

* **Canvas*&#x2A;: the speech model picker lists Endless voices and the workspace voices you can see.
  &#x2A;*"Create new voice"** opens the same form.
* **Chat**: ask for a voice by name. The chat can also create a voice, and clones only after you
  confirm consent.
* **MCP**: connected agents can list, use and create voices. Cloning still needs consent.

A voice is available only where its speech model is: if [Model
availability](/docs/governance/model-availability) turns the model off for you or it needs a higher
plan, its voices are unavailable too.