Lumen
Cute on top, deadpan underneath
Voice category
VTuber Voice Generator
A VTuber persona is a character, and characters need a consistent voice. CastDub is built for the scripted half of that work — lore videos, skits, intros, the clips where two characters talk — with a written cast sheet that keeps the persona's casting the same months apart.
Four voices to start from
Aria
Enthusiastic, slightly too loud
Tess
Dry, unimpressed, very online
Pip
The gremlin mascot everyone asks about
Every voice is available on every plan — the library is not a paywall.
Try this voice on a line of your own
No account needed. Type one line, choose who says it, and listen.
43/120
Who says it
How they say it
The scripted half of a streaming channel
A VTuber channel is usually two production lines. Live streaming, which is unscripted and real-time, and everything else — intros, outros, lore videos, animated skits, clip compilations with added narration — which is scripted, edited and often the part that actually grows the channel. The second line is where a rendering tool belongs, and it is a surprisingly large share of the work.
It is also the half where consistency is hardest. Live, you are whoever you are that day. In scripted content, viewers compare a clip from January to one from October, and any drift in the persona's voice is immediately audible.
Persona design comes first
The most common mistake is auditioning voices before deciding who the character is. Without a persona, every voice sounds wrong in a way you cannot articulate, and the search becomes endless.
A workable persona brief is three lines long: an age band, an energy level, and a characteristic attitude. "Nineteen, high energy, sincerely enthusiastic about boring things" narrows a forty-voice library to about four candidates, and those four can be auditioned in ten minutes.
Building a world with a cast
The channels that hold audiences over years tend to have more than one character: a mascot, a rival, a recurring bit character. That is difficult to produce when every voice costs a recording session and trivial when it does not, which is why multi-character lore content is one of the clearest wins here.
Characters live inside a project, and a project is one script, so keep a cast sheet with each character's library character and persona, and cast every new video from it. Then a two-year-old side character can reappear cast exactly as they were — check their first line by ear, since a new project is not guaranteed the same voice — which is the kind of continuity audiences notice and reward.
Community norms
Two norms matter and both are about honesty. Disclose that a voice is generated — the community's tolerance for this is much higher than its tolerance for finding out later. And never clone another creator's voice, even affectionately; in a scene built on persona identity it is read as identity theft, and correctly so.
Voice cloning here works from one recording only: you reading a short consent statement aloud — which makes the legitimate case, cloning your own voice so you can script faster, straightforward, and the illegitimate case impossible. A cloned voice reads your lines but does not act out emotions, so keep the expressive moments for your live voice or a library character.
Scripted clips versus live persona
A persona that exists both live and in scripted content has a consistency problem that no tool solves entirely: your live voice and a generated voice will not match. The channels that handle this well do not try to hide the difference — they use the generated voice for a distinct kind of content, such as lore videos, animated segments or the mascot character, and let the live streams be themselves.
Trying to make scripted clips sound like the live persona invites a comparison you cannot win. Giving the scripted content its own identity sidesteps it entirely, and often produces something the channel did not have before.
Building recurring characters
The most durable channels in this space have a cast: a mascot, a rival, a recurring bit character with three catchphrases. Previously that meant a creator doing several voices themselves, which is a specific skill most people do not have.
A cast that costs nothing to add changes what kind of content is possible, and the pattern worth copying is a small number of very distinct characters who reappear rather than a large number of one-offs. Audiences form attachments to characters they see repeatedly, and attachments are what bring people back.
Script to audio in a few steps
- Define the persona before the voice
Age, energy level, what they are sarcastic about. A persona document makes casting fast; without one you will audition forty voices and like none of them.
- Audition on in-character lines
Use lines your persona would actually say — a greeting, a complaint, a bit. Neutral sample text tells you nothing about whether the voice fits a character.
- Write the casting down immediately
Library character, persona and default emotion. Characters live inside one project, so every future clip is cast again from that note — and checked by ear, since a new project is not guaranteed the same voice — which is how the persona stays the same across a year of uploads.
- Cast the supporting characters too
Lore videos and skits need a second and third voice. Casting them properly is what separates a channel with a world from a channel with a filter.
- Export stems for editing
Clip editing involves a lot of retiming. On Pro, per-voice stems let you slide lines around without re-rendering anything.
Frequently asked questions
Can I use this to stream live?
No. This renders written scripts, it is not a real-time voice changer. For live streaming you want a real-time pitch and formant tool; CastDub is for the scripted content around the stream — intros, lore videos, skits, clip voiceover.
How do I keep the voice consistent over a year?
A written note of the casting — library character, persona, default emotion — used for every new project. Consistency fails when someone re-picks a voice from memory six months later, not because the model changes. Characters do not carry between projects and the same voice is not guaranteed in a new one, so listen to the persona's first line before every export.
Can I make a voice that matches my model's design?
You can match the register — age, energy, brightness — which is what viewers actually respond to. Write down three adjectives for the design and filter the library by those style tags rather than auditioning at random.
Is it acceptable to use a generated voice as my persona?
That is between you and your audience, and the answer most communities land on is that disclosure makes it fine. Undisclosed is where it goes wrong, because VTuber audiences are unusually invested in the person behind the model.
Can I clone another VTuber's voice?
No. Cloning here covers only your own voice, it will never allow this, and it is one of the most actively policed forms of harassment in that community. Build an original persona instead.
What plan suits a VTuber channel?
Basic for solo clips, Plus once you are producing multi-character lore videos — the cast size is what matters there. Pro adds stem export, which is worth it once you are mixing the voices against music.
What people build with these voices
Cast your first scene tonight
Paste a script, let CastDub assign a voice to every character, and export a finished drama.
Create for freeNo credit card. Free gives you a one-time pot of credits.