> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rewatch.studio/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice: make it speak and create a voice

> Give the exact text and a one sentence tone direction, then create your own voice from a description.

This page covers two things: making a voice say a text (the “Voice generator” tool), and creating a custom voice (the “My voices” page).

## Making a voice say a text

You give the text to say, or you ask the assistant to write it. It launches the synthesis with two pieces of information: the exact text, with no stage directions, and a one sentence tone direction. It picks the voice from the list, or you choose it yourself in “Voice” (“My voices”, catalog).

```text theme={null}
Say “[the exact text]” in a [acting adjectives: warm, calm, friendly, rushed] tone.
```

> [tab] Weak
>
> ```text theme={null}
> Read this with a nice voice: Once upon a time there was a forest.
> ```

> [tab] Improved
>
> ```text theme={null}
> Read in a deep, calm voice: Once upon a time, deep in the forest, there was a cabin that nobody had ever opened. Storyteller tone, a smile in the voice, pause before “ever”.
> ```
>
> The text is complete, the tone is a concrete sentence, and the pause is placed.

A text that is too long is cut by the assistant into several generations. To have the text written: “Write and voice a two sentence hook for a cooking video”.

## Creating a voice from a description

In “My voices”, “Describe a voice” takes a name (60 characters) and a description (500 characters). Say the gender, the approximate age, the timbre, the grain, the pace, the accent.

```text theme={null}
[Deep, clear, high] voice of a [man, woman] of [age] years old, [grain: husky, silky, nasal], [pace and energy], [region] accent.
```

Example provided by the app: “Deep, calm voice of a 50 year old man, slightly husky, southern accent”.

A variant offers three voices to listen to before keeping the one you like. It accepts a longer description (1,000 characters): add the role (calm storyteller of true stories) and the acting (pauses before each reveal). Each batch of three proposals costs a few credits, and so does the voice you keep.

> [tab] Weak
>
> ```text theme={null}
> A cool voice
> ```

> [tab] Improved
>
> ```text theme={null}
> Deep voice of a man in his forties, slightly husky, Boston accent, calm storyteller of true stories, pauses before each reveal.
> ```

You can also clone your own voice by recording a sample: it is your voice, or the voice of a person who gave you their consent. Custom voices depend on your plan and your quota.

## Common mistakes

* Putting a stage direction in the text (“(he laughs)”): it would be read aloud. Put the acting in the tone direction.
* A tone in several paragraphs: one sentence is enough.
* Describing the voice with the emotion of a single line: describe the voice, not what is said.
* Naming a real or famous person: describe the timbre.
* Writing in one language and choosing a voice from another: set “Language” and pick a voice that speaks it.

## Settings that go with it

* **Voice**: search by name, filter by group (“My voices”, catalog).
* **Language** of the voice.
* A voice created here can then be pinned to a series character: see [Voice, mascot and intros and outros](https://docs.rewatch.studio/series/voice-mascot-jingle.md).
* Start with a short text before a long one: see [Spending credits wisely](https://docs.rewatch.studio/models/credits.md).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.