Welcome to the Synthesizer V Forums! This post includes a list of helpful links and frequently-asked questions, so please check here before making a new topic.
First off – This is an official forum, but Dreamtonics does not actively participate in the discussion or engage with users here. Please keep in mind that the people here are users just like you. If you need an official response from Dreamtonics, contact them via email at [email protected].
Similarly, if your topic requires the attention of the development team (feature requests, product feedback, etc.), send your message directly to Dreamtonics via email. There is no guarantee that the developers will see anything posted on these forums, so the forums are best treated primarily as a discussion space and an opportunity for users to help each other.
Synthesizer V Studio is a singing synthesizer created by Dreamtonics, which creates synthesized vocal sequences based on the notes and lyrics input by the user via a specialized piano roll.
The synthesized vocals are based on voice databases, which are commercial products created by Dreamtonics and their partnered third-party developers. Some of these voice databases have free “lite” versions (see below).
Each voice database is based on the voice of a human voice provider. Depending on the details of their contract, the voice provider for a voice database is not always publicly known.
SynthV Studio is a virtual instrument similar to a piano or violin synth; it is not a voice changer or voice filter. There are no features to transform or morph a recording of your own voice.
If you’re new to Synthesizer V Studio, it is recommended to check the Quickstart section of The Unofficial SynthV Studio User Manual, which covers installation of the software as well as everything you need to know to start generating vocal sequences.
This depends entirely on your goals. There’s a lot to learn, but you can still create relatively convincing sequences with minimal effort.
To use guitar VSTs as a comparison, it’s very common for digital musicians to create nonsensical guitar solos or unnatural sounding chords when using a virtual guitar. There is some amount of knowledge required about the instrument to use a VST effectively, and even people familiar with the instrument will need to learn how to translate their ideas into a MIDI format and configure the VST correctly.
These same ideas all apply to vocal synthesis as well. Luckily, with the AI-generated pitch patterns introduced by Synthesizer V Studio, it’s a lot harder to accidentally create completely unnatural or nonsensical results than it is with most virtual guitar plugins. Users will benefit from knowledge about singing techniques, phonetics, and the human vocal tract, but you don’t need this knowledge to get started.
As mentioned above, this all depends on your goals. If you want to create synthesized vocals that are indistinguishable from a human vocalist, you will face more nuanced challenges and have more to learn. If you are creating EDM-style or heavily processed vocals with a stereotypical “Auto-Tune” feel, you might be able to simply keep the quantized phonetics, remove all AI-generated pitch patterns, and call it a day (though there’s still plenty you can learn to improve the results).
Keep things simple at the start. There are a lot of powerful tools in the software to customize pitch patterns, timbre, phoneme timing, pronunciation, and more, but these topics can get overwhelming if you try to tackle them all at once.
Dreamtonics International Store
- Dreamtonics Taobao (for Chinese buyers)
- Quadimension only sells via Taobao. If you are an international buyer, you may have difficulty making a Taobao account.
- Many users have had success buying via a proxy service, however please be mindful that this costs extra as you are paying a third party company to make the purchase on your behalf.
- Eclipsed Sounds
- Voicemith (International)
- Synthesizer V Studio Basic
- Mai (free voice database for Pro users)
- Links for all “Lite” voice databases: SynthV Resources & Guides
- This is a user-made website which directs to official download links
Yamine Renri registration form
- This registration form is processed manually. It may take some time for Volor to send you a license code and download link.
- AHS MyPage (for product registration and download of digital extras)
- Dreamtonics Website
- Dreamtonics Store Downloads (paid products only)
- Dreamtonics Twitter (English, Japanese)
- Dreamtonics YouTube
- Dreamtonics - [email protected]
- Dreamtonics (business inquiries only) - [email protected]
- AHS - サポート｜製品サポート｜AHS(AH-Software)
- Cleverbridge Purchase Lookup - https://www.cleverbridge.com/?scope=cusecolp
- Quadimension (Beijing Photek) - [email protected]
- ANiCUTE (Volor/Animen) - [email protected] or [email protected]
- Eclipsed Sounds - [email protected]
- AUDIOLOGIE - [email protected]
- Voicemith - [email protected] or [email protected]
- The Unofficial SynthV Studio User Manual
- SynthV Wiki
- UtaFormatix (project file conversion between different vocal synths)
The only official instructional content is the Dreamtonics video tutorial series on YouTube.
Search these forums for someone else with the same issue. If you can’t find an existing topic, consider making your own, perhaps other users will be able to assist you.
If you need a response from Dreamtonics, you must email them directly ([email protected]).
The best way to report a bug or provide feedback to Dreamtonics is by email.
There is an older product simply called “Synthesizer V” (also known as “Synthesizer V Editor”, “R1”, “Gen-1”, etc.), however this was based on a different synthesis engine that is not compatible with any of the current voice databases. All voice databases for the original release of Synthesizer V have been ported or re-released for SynthV Studio.
This is what Synthesizer V Studio looks like. If the software you installed looks different, then you’ve downloaded the wrong thing.
The Basic edition of Synthesizer V Studio has a limited feature set compared to the Pro edition. The list of features that are limited or unavailable in the Basic edition can be found on the store page for Synthesizer V Studio Pro.
Paid voice database products can be used with either edition of the software, however the feature limitations of the Basic edition will often mean you cannot leverage the full capability of the voice database.
There is no trial version of SynthV Studio Pro.
Lite voice databases are lower quality versions of paid products, which are available for free but have limited functionality.
- No vocal mode support
- No cross-lingual support
- Reduced vocal range
- Lower quality output (more noise/artifacts)
- Lite voice databases are restricted to the “Prefer Speed” render mode in the Voice panel
- Less natural generated pitch patterns
Lite voice databases are subject to the following terms:
- 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 must clearly state the name of the voice database used and the fact that a Lite version is used
- You should acknowledge that the Lite version does not represent the quality of the full version of the same voice database. Dreamtonics makes no quality or quantity guarantee on the Lite version of a voice database.
No. Synthesizer V Studio originally released in July 2020, but the AI synthesis functions weren’t added until December of 2020. For a short time after, many voice databases had both “Standard” and “AI” versions.
Development has now shifted exclusively to AI voice databases.
Standard voice databases are not compatible with many features, such as cross-lingual synthesis, vocal modes, sing/rap pitch modes, AI retakes, phoneme strength adjustment, and tone shift.
List of Standard voice databases which do not have an AI counterpart
- Kotonoha Akane/Aoi
- Yamine Renri
List of Standard voice databases which also have an AI version
- Koharu Rikka
- Kyomachi Seika
- Tsurumaki Maki
The officially supported languages are Japanese, English, Mandarin, and Cantonese. Rap functions currently only support English and Mandarin Chinese.
AI voice databases can use cross-lingual synthesis to sing in any supported language, however each voice database still has a “native” language and it is normal for them to have an accent when utilizing cross-lingual synthesis.
It is possible to create an approximation of an unsupported language using the existing phonemes, however this will often result in awkward timing and pronunciation.
When you purchase a product you will receive two things in the order confirmation email; a download link, and a product activation code. Do not delete your order confirmation email, and be sure to save your product activation code in a safe place.
Each activation code has three uses to account for hardware failure or accidental loss, however not all products allow for multiple concurrent uses, and all licenses are only valid for a single user (so even if a license allows two concurrent installations, it must be the same person who is using the software on those computers).
The Dreamtonics voice database EULA can be found on the Dreamtonics website, however the terms will vary between developer. The license terms can always be found in the installation directory for the product.
Activating a product requires an internet connection and will reduce the number of uses for the activation code by one. An internet connection is not required once the product is activated.
In order to reclaim a use of the activation code, you must deactivate the software before uninstalling it. This allows you to move the activation to new computers without limit. The extra uses for each code allow for situations where deactivation is impossible, such as hardware failure. Deactivation requires an internet connection.
Your activation may be automatically invalidated if the computer is no longer detected as the same one the product was activated on. This can occur if you replace computer hardware, upgrade your motherboard firmware, or reinstall your operating system without first deactivating SynthV Studio.
Yes! Commercial use is subject to the license terms of the voice database. You can see the terms for Dreamtonics voice databases on the Dreamtonics website, while the terms for voice databases from other developers may vary.
At the time of writing, all paid voice database products allow for commercial use, however some require you to contact the developer prior to publishing your song.
Please be mindful that use of the synthesized voice and use of the copyright image and associated character design are often subject to different terms. The license for each product can always be found in its installation directory.
No, there is no requirement to give credit or attribution to either Synthesizer V Studio or the voice database (unless you are using a Lite version, as mentioned above).
The main restriction on attribution is that you cannot claim the synthesized vocals were produced by different means. If you used SOLARIA for your song, you must either not attribute the vocals at all or credit the voice/vocalist as “Solaria”.
You may not claim that a human or different vocal synth was the original source of vocals which were created with Synthesizer V.
Synthesizer V Studio Basic can only be used standalone. The output can be rendered to a wav file and then be imported to your DAW just like any other vocal recording.
The Pro edition can also be used as either a VST3 or AU plugin.
The plugin does not have ARA2 support, so you will need to enter tempo and time signature changes manually.
Track color is automatically set when a new track is created, or will be the same as the original track when after a track has been duplicated.
Track color can only be set manually by using scripts, which requires the Pro edition of the software ([Script] トラックの色を変更／TrackColorChanger (containing many presets)).
The track color will affect the preview in the arrangement panel, as well as the thin lines in the background of the piano roll which show note positions from other tracks.
Note color in the piano roll for the current track is based on each note’s Pitch Mode setting in the Note Properties panel, not the track’s assigned color.
Glottal effects have not yet been implemented for Synthesizer V Studio.
There is no support for user-created voice databases for Synthesizer V Studio. If you are a company looking to create a commercial product, send your proposal to Dreamtonics at [email protected].
Other options for user-made vocal synths or voice changers include UTAU, DeepVocal, NNSVS, diff-svc, and DiffSinger.
You can find more extensive discussion of the topic here: Custom voicebanks