Is there a demo voice or a demo setting so I can try this out and see if its good for me. I downloaded a free voice mai but it asked for a serial number. At the moment all I can use is a whistle sound.
Any help appreciated. Been wanting something like this for years.
Mai is only free for people who own the Pro edition.
If you are using exclusively free options, you need SynthV Studio Basic and a “lite” voice, which are available from the same site you got Mai from. (some lite voices are also available from other locations, such as the Eclipsed Sounds website for “Solaria lite”)
Check here for more info:
edit: Now that I’m at my PC, here are links to the Basic edition and the official Google Drive locations for each English “lite” voice:
Basic / Pro differences are listed on the store page:
Synthesizer V Studio Basic
Synthesizer V Studio Pro
Tracks
Up to 3 tracks per project
Unlimited
Rendering threads
Up to 2 threads
Unlimited
Note level Cross-lingual synthesis
Not supported
English, Japanese, Chinese
Auto Pitch Tuning
Fixed pattern
Customizable
Auto Ornamentation
Not supported
Customizable
Aspiration output
Not supported
Customizable
Note detuning
Not supported
Supported
Tone Shift parameter
Not supported
Supported
Scripting
Not supported
Lua, Javascript
Plugin
Not supported
VSTi, AudioUnit
Vocal Mode
Not supported
Supported
AI Retake
Not supported
Supported
MIDI keyboard support and Metronome
Not supported
Supported
As for paid vs lite voices, lite voices are lower quality, lack some features (ie, no cross-lingual synthesis or vocal modes), and are subject to the following conditions:
You may not use the Lite version for commercial purposes.
You may not publish your work using the Lite version on behalf of an organization.
If you wish to publish a work created using the Lite version, you should clearly state the name of the voice database used and the fact that a Lite version is used.
Auto Ornamentation is an automated task which will break up the notes into smaller parts to introduce pitch deviations. This is sometimes called “note bending” by people who do it manually.
Aspiration Output means you have an option to render the vocal aspiration (breathiness, sibilants, etc.) to a separate track so you can mix them differently in your DAW.
Vocal Mode is a set of sliders available to paid AI voices which modify the behavior of the voice. For example, Solaria has options for Clear, Soft, Airy, Power, Passionate, Solid, and Light.
AI Retakes are a feature that lets you generate multiple different versions of the same note and pick your favorite.
lite voices are “lower quality” in the sense that they have less AI training data, which means they don’t have as realistic transitions and vibrato, and tend to have more noise and narrower vocal range. There are some other nuances here but that’s the main difference.