Beyond words

An AI character that sends photos and speaks

The same character you write with can draw the scene you are in, answer out loud in their own voice, and look at the photo you just sent. Nothing to switch on, and the face stays the same.

Talaforge › An AI character that sends photos and speaks

Text-only roleplay hits the same wall every time: you have been building a scene for an hour and there is no way to see it. The character describes a room and you picture your own version of it. The character describes themselves and the picture drifts a little further from the last one every session.

Three things close that gap, and none of them needs configuring.

They draw the scene you are in

Ask for a picture and the character draws the moment you are actually in, not a generic portrait. The result arrives in the conversation, not in a separate gallery you have to go and check.

The part that matters is consistency: the same face every time, because the look is locked rather than re-rolled. Most image tools give you a new person on every generation, which is why character art from them never feels like the same character twice.

You pick which engine draws it. Different engines have genuinely different hands — one is better at faces, another at light and atmosphere — and the choice is per image rather than a setting you configure once.

They answer out loud

Replies can arrive as a real Telegram voice message — waveform, scrubbing, speed control, the same object as a voice note from a person. Not an audio file attachment you have to download.

Every character gets a voice that fits them. You can browse the available voices and preview one before committing, and the behaviour has three settings: off, on request, or automatic.

These are voice messages, not a phone call. There is no live conversation and nothing listens to you — you type, and the reply happens to arrive as audio.

They look at what you send

Send a photo into the chat and the character sees it. The view from your window, the outfit you were asking about, a drawing you made — and the reply is in character about what is actually in the image, not a generic acknowledgement.

This is the one that surprises people, because it changes the direction of the medium. Up to that point you have been describing your world in words. Now you can just show it.

Nothing to switch on

There is no settings page standing between you and any of this. Photos can arrive on their own as a scene moves, and the speaker button sits under every reply from the first message.

Both run on energy, topped up with Telegram Stars inside the chat. You can see how much is left at any moment.

What happens to what you send

A photo you send is relayed to a third-party provider so the character can answer about it, the same way your text is relayed to generate a reply. This is written down in the policy rather than implied.

Nothing you send is used to build a public gallery, and images generated in your conversation land in your conversation.

Why the face staying the same is the hard part

Generating a beautiful image is easy now. Generating the same person twice is not, and it is the difference between illustrations and a character.

The look is fixed when the character is created and applied to every render afterwards, so a scene in a cafe and a scene on a street two weeks later are recognisably the same person. Nobody uploads a reference photo and nobody adjusts a setting — the consistency is a property of the character, not something you maintain.

Can an AI character send me pictures of themselves?
Yes. Ask for one and the character draws the moment you are in, with the same face every time because the look is locked when the character is created rather than re-rolled per image. The picture arrives in the conversation.
Why do AI-generated characters look different in every image?
Most tools treat each generation independently, so you get a new person each time. Consistency requires the appearance to be fixed as a property of the character and reapplied on every render, which is what happens here — no reference upload needed.
Can the AI character speak in a real voice?
Replies can arrive as native Telegram voice messages with a waveform and speed control. Each character has a fitting voice you can preview before choosing, and you can set replies to off, on request, or automatic.
Can I send a photo to an AI character and have it understand?
Yes. Send a photo into the chat and the character answers in character about what is actually in it — a view, an outfit, a drawing. The image is relayed to a third-party provider to be read, which is stated in the privacy policy.
Do images and voice cost extra?
They run on the same energy as conversation, topped up with Telegram Stars inside the chat, and you can see the balance at any time. A render that fails is not charged.
Can I turn images and voice off?
Yes, either one independently. Nothing needs enabling to start with and nothing needs to stay on.
Can I choose which image engine draws the picture?
Yes, per image. Different engines are better at different things — faces versus light and atmosphere — so it is a choice you make in the moment rather than a setting.
Make a character in Telegram →

Read next