Skip to content
Powered by Mera

Avatars.

An instant presenter for every idea.

Give your words a face and a voice. Mera Avatar turns a script into a lifelike performance—lip-synced, expressive, and ready when you are.

From a single frame to a full performance
The presenter problem

Someone has to
say it.

Avatars is Relam’s instant presenter studio. A message lands harder when a person delivers it—and that used to mean cameras, schedules, and takes. Now it means a script.

Mera Avatar carries a consistent face and an emotional performance through a video of up to 120 seconds. The voice moves the mouth. The feeling moves the face.

THE BRIEF

“Introduce our new cohort program, like you’re welcoming an old friend.”

Generated portrait of a man in a dark suit overlooking the Dubai skyline at sunset.

The script, the face, and the voice—then generate.

The scriptIntroduce our new cohort program, like you’re welcoming an old friend.
Avatar attached · Studio referenceVoice · Eve Live · Warm
Language · EnglishStyle · Welcoming
Mera Avatar

Illustrative interface. The performance shown is Relam-generated.

Where presence comes from

More than
a moving mouth.

Mera listens to the voice itself—pitch, pauses, the lift at the end of a sentence—and lets the delivery lead the performance.

A presenter who never needs a reshoot, never misses the brief, and speaks the language you choose.

Podcast presenter at a microphone with a voice waveform and video frames.
The voice leads
The mouth follows

The waveform is the performance. Mera keeps the voice and the lip sync together for the whole take, so every word lands the way it was meant.

Built on Mera

Motion that
obeys physics.

01 / Natural motion

Weight and balance.

Hair, cloth, and breath follow the small physics of being human. Nothing floats unless the brief says so.

02 / Light that behaves

Rendered like a camera sees.

Mera keeps the light honest from frame to frame, so the scene holds together instead of flickering between takes.

03 / Emotion that reads

A subject that stays.

One consistent face carries feeling across the whole take—up to 120 seconds of it, with continuity intact.

From script to screen

Four choices.
One performance.

Everything a director would ask for, decided by you in a single pass.

  1. 01 / The face

    Choose who presents.

    Start from a reference image with the permission to use it—your own, a licensed likeness, or one generated in Visuals.

  2. 02 / The words

    Write the script.

    Say what the presenter should deliver. The words set the emotion; Mera handles the phrasing.

  3. 03 / The voice

    Set voice and language.

    Pick the voice, the style, and the language, then review the estimate before anything is generated.

  4. 04 / The take

    Generate the performance.

    Mera renders the take with lip sync and expression—up to 120 seconds—straight into your Library.

Effortless by design

If you can brief it,
you can ship it.

No timeline. No keyframes. No rigging. The face, the words, and the voice are chosen in plain words—everything else is Relam’s to coordinate.

When something should change, change the words—not the schedule. The next take starts from the brief you already wrote.

01 · The brief

“Introduce our new cohort program, like you’re welcoming an old friend.”

02 · The faceGenerated portrait of an older potter shaping clay on a wheel in a sunlit workshop.
03 · The take
The voice booth

Choose even
the voice.

Set it in the same pass as the script—your own voice, or a preset near-human one.

Your own voice

Sound like you.

Attach a voice reference you have the right to use, and keep your presenter sounding consistent across every take.

Eve Live presets

Near-human, out of the box.

Preset voices powered by Eve Live breathe, pause, and land a sentence like a person—no recording booth required.

Meet Real-time Voice
The old way

No studio.
No reshoots.

A presenter video used to be a production. Now it is a paragraph.

A traditional shoot

Crews, calendars, reshoots.

Booking a presenter means scheduling around people, paying for the session, and re-shooting every change of mind.

Mera Avatar

A script, a face, a voice.

Change the words and regenerate. One consistent presenter for every update, in the language you choose—without booking anyone.

Explore Workflows
Avatars FAQ

Before you begin.

The avatar family of the Mera model by Skytells. It carries a consistent subject and emotional performance through videos of up to 120 seconds.
Use a face and voice you have permission to use—your own, a licensed likeness, or references generated in Relam. Using a real person’s likeness or voice requires their permission.
Up to 120 seconds, with the subject and the emotional continuity held across the whole video.
Finished avatar videos land in your Library, ready to share or use in your next workflow.
Relam Avatars

Say it like you mean it.

Your next presenter is a script away.

Keep performing