> ## 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.

# Talking avatar and AI podcast

> Write the text of an avatar speaking to camera or the dialogue of a two host podcast.

Two tools from the “UGC” family put real looking people on camera: “Talking avatar” (one person alone) and “AI podcast” (two hosts at most). The video model itself says each line, with the voice fixed at the first speaking shot.

## Talking avatar

A photo of you or a generated person says your text, filmed like on a phone, lips synced. The field is called “What you write”, with two choices:

* **“My script”**: said word for word.
* **“An idea”**: the AI writes the text, the way people talk to camera.

### The form that works

“My script” mode:

```text theme={null}
[Hook in one sentence]. [Three short ideas]. [Call to action].
```

Write the way you talk: short sentences, one filler word (“well”, “honestly”), a real pause. Count about 20 words for 15 seconds.

```text theme={null}
Okay, so, honestly, I tested the 5 a.m. routine for a month. First thing: I lay out my stuff the night before. Second: no phone before 7. Third: I move for ten minutes, even outside. Tell me in the comments if you'd last three days.
```

“An idea” mode: give the topic and the tone, the AI writes the text.

```text theme={null}
Three tips to sleep better, told like to a friend.
```

### Before / after

> [tab] Weak
>
> ```text theme={null}
> Text about sleep.
> ```
>
> No precise topic, no tone, no audience.

> [tab] Improved
>
> ```text theme={null}
> Three concrete tips to sleep better when you work late, told like to a friend, warm tone, no jargon, 30 seconds.
> ```
>
> A topic, an audience, a tone, a length.

### Avatar settings

* **Limit**: 1,200 characters. The length is deduced from the text (about 2 words per second, between 10 s and 4 minutes). In idea mode, you choose the length.
* **Photo**: optional. A sharp, front facing, well lit face is used as is. Without a photo, a person is generated; “Consistent character” keeps their face the same from one shot to the next.
* **Voice**: “Automatic” creates the voice at the first shot and keeps it afterward. Pick a voice to impose it.
* **Avatar model** and **Resolution**: they set the quality of the render and the price per second.
* **Subtitles**: on by default. **Music**: off by default.
* A speaking shot lasts 15 s at most: a long text is cut into several shots.

## AI podcast

A two voice dialogue, one host per shot, full screen or split screen: the editing alternates between full screen on the one speaking and a vertical split screen, one host on top, the other at the bottom, where the listener reacts.

### The form that works

Start each line with the host's name in square brackets, like `[Alex]`. Two hosts at most.

```text theme={null}
[Alex] Welcome to the podcast. Today: why we put everything off until tomorrow.
[Sam] Glad to be here. And I almost didn't come.
[Alex] Great start. So, is it laziness?
[Sam] No, it's emotion management. We avoid what stresses us out.
```

No script at hand? Write a topic of a few words (at least 3) in “Generate a dialogue with AI”: the dialogue is written into the field and you review it before launching. It is a billed text call.

### Before / after

> [tab] Weak
>
> ```text theme={null}
> Alex: hello
> Sam: hello, we talk about everything
> ```
>
> No brackets, no topic, lines with no substance.

> [tab] Improved
>
> ```text theme={null}
> [Alex] Today, a touchy subject: does working from home make you more productive?
> [Sam] Me, I say yes, but only on Tuesdays.
> [Alex] Tuesdays? Explain.
> [Sam] It's the only day without meetings.
> ```
>
> The hosts are in brackets, there is a disagreement and follow ups, like in a real conversation.

### Podcast settings

* **Host photos** (optional): one photo per host, named as in the dialogue. Without a photo, the host is generated; “Consistent hosts” keeps their face the same from one shot to the next.
* **Limit**: 1,200 characters, default length 30 s. Subtitles on, music off.
* Each host has a single image and a single voice, reused on all their lines.

## Common mistakes

* **Avatar: a text written to be read**: long sentences sound fake. Cut and talk.
* **Avatar: a group photo or a profile shot**: give a sharp, front facing face.
* **Podcast: three hosts or more**: two at most.
* **Podcast: a different name on each line**: keep exactly the same names: they are used to recognize each host and their photos.
* **Going over 1,200 characters**: the field stops. Shorten, or make several videos.

See also [Paste your script](https://docs.rewatch.studio/video/script.md) and [the voice](https://docs.rewatch.studio/tools/voice.md).


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