Your Fifth Day in MITO: Give It a Voice and Something to Listen To
A video without sound feels unfinished, and nobody can ever tell you why. Today is the why.
Day 5 of 8 in the MITO onboarding series. See all eight days →
Day four was about the brief. Today is about the half of a video nobody mentions until it is missing.
Two things, both short. Your own voice, and the sound around it.
Clone your voice
Stock voiceover is fine until the piece is yours. Then it is the one thing that gives it away.
Cloning a voice, just over a minute.
Where it lives. Plus icon in the toolbar, then Audio. Bottom left, switch Instrumental to Voice over. Click Voice, then Clone a voice.
Two ways in. Record yourself on the spot, up to twenty seconds, or drop in a clip of your voice, including the audio off a video you already made.
If you freeze. There is a Try this link at the bottom with lines to read. Use it. Reading something neutral out loud gives a better clone than improvising.
Trim, then name it. Cut down to the part worth keeping or record again, give the voice a name, pick its language, confirm you have permission to use it, and create.
It is selected for you straight away. After that it sits under Choose a voice, in My voices, in any project.
Generate the sound around it
Sound effects and music, a minute and a quarter.
Same plus icon, same Audio panel. Pick the type first: instrumental music, a song with lyrics, a voice, or a sound effect.
Effects. Describe the physical thing. Footsteps on wet pavement. A car door closing. Rain on a window. Foley is what makes a shot feel like somewhere rather than something.
Music. Describe style and mood, not genre. Calm ambient pads, slow tempo, no drums. Two questions first: what is the mood, and what is the music actually for. If you need the full picture on scoring a piece, there is a guide on choosing music.
Or skip all of that. Ask Director: add rain sounds and soft ambient music to this clip. It generates both, puts them on the canvas, decides where each sound belongs, trims them and lays them on the Timeline. Then you press play.
Before you close the tab
Clone your voice from a twenty second recording, then have it read one line of a script.
Then make one sound effect and one ambient track, and put both under a short clip you already have.
Play the clip silent, then play it again with the sound. That second playback is the entire lesson, and it takes about six minutes to get to.
Tomorrow is avatars, and getting one of them to speak another language.
The short version. Twenty seconds gives you your own voice. Effects are physical descriptions, music is mood and purpose. Director will do a first pass of both if you ask it to.
All of these walkthroughs are inside MITO too, under Tutorials in the sidebar.
Frequently asked
- How long a recording do I need to clone my voice?
Up to twenty seconds, recorded in the browser. If you would rather not record, you can upload a clip of your voice instead, including the audio from a video you already have.
- Where is voice cloning in MITO?
In the toolbar, click the plus icon and choose Audio. At the bottom left, switch Instrumental to Voice over, click the Voice box, then Clone a voice.
- What if I do not know what to read?
The recorder has a Try this link at the bottom that gives you lines to read out loud. It exists because reading something neutral produces a better clone than improvising.
- Can I trim or redo the recording?
Yes. Drag the trim handles down to the part worth keeping, or record again. It is worth doing, because the clone is only as good as the twenty seconds you feed it.
- Do I need permission to clone a voice?
Yes, and MITO asks you to confirm it before the voice is created. Clone your own voice, or someone’s who has explicitly agreed to it.
- Where does my cloned voice show up afterwards?
It is selected automatically right after you create it. Later it lives under Choose a voice, in My voices, and it is available in any project, including inside Avatar Studio.
- What kinds of audio can MITO generate?
Four: instrumental music, a song with lyrics, a voice, and a sound effect. Pick the type first, then describe what you want.
- How should I describe a sound effect?
Concretely and physically. Footsteps on wet pavement. A car door closing. Rain on a window. These are the foley sounds that make a shot feel like a place rather than a render.
- How should I describe music?
By style and mood rather than by genre name. Calm ambient pads, slow tempo, no drums. Before you write anything, answer two questions: what is the mood, and what is the music doing for the piece.
- Can Director do the audio for me?
Yes, and for a first pass it is usually the better route. Ask it to add rain sounds and soft ambient music to a clip. It generates the audio, puts it on the canvas, works out where each sound belongs, trims it and lays it on the Timeline, so you can play the result straight back.
The AI tool for cinematic video.
Generate, direct, and publish professional videos — powered by the best AI models.
More posts
