
What happened
AHS launched two voice databases for Synthesizer V 2 on September 29 — the female Synthesizer V 2 AI Nanami and the male Synthesizer V 2 AI Kohki — each priced at 9,680 yen.
Why it matters
The two voices are sold as add-on databases, so buyers appear to be users who already run Synthesizer V 2 and want more vocal variety on top of it.
What to watch
The fuller vocal-style feature hinges on pairing them with the separately sold Synthesizer V Studio 2 Pro, so the practical value depends on whether users already own that product.
WHO IT HITSMusic producers, hobbyist songwriters, and Vocaloid-style creators who already use Synthesizer V 2 are the ones deciding whether to add these two voices to their library.
Summaries like this, in your inbox every morning.
Synthesizer V is Dreamtonics' singing-synthesis software, which lets users produce natural-sounding vocals without a human singer. The version 2 release, which AHS is selling voice databases for, is built around a newer AI synthesis engine that speeds up rendering and refines the pitch-editing tools for smoother, faster work.
The two databases are positioned at opposite ends of a vocal range. Nanami is described as a female voice with a clear, penetrating tone that carries across rock, pop, and ballads, while Kohki is a male voice with a bright, refreshing character aimed at upbeat pop-rock and electro as well as slow and mid-tempo pop. AHS is not selling a single general-purpose voice but two distinctly styled ones, which suggests the appeal is targeted variety rather than one catch-all option.
One structural point shapes how the launch is likely to be received. The vocal style feature that broadens expressiveness only becomes available when these databases are paired with the separately sold Synthesizer V Studio 2 Pro, so the fullest use of either voice appears to assume an existing owner of that product. The outcome for AHS therefore hinges on how many current Synthesizer V 2 users see enough difference between Nanami and Kohki to buy in at 9,680 yen each.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
Hugging Face launched the Open TTS Leaderboard, ranking models by word error rate (WER/CER), H200 GPU speed me…

The Tokyo District Court dismissed Kenjiro Tsuda's demand that TikTok remove AI voice-clone videos, citing pri…

DeepL opened general availability of real-time speech-to-speech translation in DeepL Voice, supported by a new…

ElevenLabs released Eleven v4, which handles up to 10,000 characters per request and supports more than 90 lan…

NTT West's VOICENCE company said it will open a free "Voice Consultation Desk" on September 28, 2026

AWS published Part 1 of a tutorial that deploys Qwen3-TTS on Amazon SageMaker AI using the vLLM-Omni Deep Lear…
