Hi everyone,
We’ve been working on something for a long time, and we’re finally ready to start showing it to you. There’s a teaser now live, ahead of the full reveal, soon:
We’re keeping the details to ourselves for now.
What do you think is coming? Let us know in the replies, we’ll be reading.
What a waste of time. A lame video with no clue and not even the slightest interesting piece of information.
I really hope it’s not a paying upgrade…
You’d better focus on GREATLY improving French and other languages…
SIGH…
Okay - perhaps spomething with surround. Placing voices i.e. of a choir in a 3D room 
I find the new logo shown at the end of the teaser video interesting.
It looks similar in design to the current Synthesizer V logo, so I’m curious whether this is related to a completely new program or a new innovation that will be brought to Synthesizer V.
I have been thinking about a few possibilities based on the speaker shown in the teaser and the new logo design.
Like some other users have suggested, it might have something to do with surround sound. Also, the shape of the logo looks similar to the letter “X”. I feel that the meaning behind this shape could represent a more natural transition and intersection between different aspects of human nuance.
Of course, I cannot immediately think of a specific result or feature that this could lead to.
Could it be a new technology that allows us to create vocal modes that are not limited to existing voice banks, or enables smoother and more flexible transitions between vocal modes?
Could it be Synthesizer V Studio 3 or a talking feature?
judging by the low bass sound at the end and logo, I think it’s gonna be an DAW or an Instrument synth (hopefully not a genAI music maker). very odd since dreamtonic has teamed with bitwig to give us a free daw (never received it despite signing in)
First of all, I’m only a user, so I can’t really know what this teaser is meant to represent.
However, your mention of a “talking feature” made me think of Dreamtonics’ TTS engine.
If I remember correctly, it is currently used in AH-Software’s Voicepeak.
As far as I know, Voicepeak is not just a simple narration tool, but also has features that allow it to express emotions. It does not simply speak the words, but also conveys the emotions contained within the speech. With that in mind, when I looked at the new logo revealed in the teaser again, I started to wonder if this might be less about the release of a completely new program, and more about adding something like an “Expression Mode” alongside the Vocal Modes that currently exist in Synthesizer V 2.
Of course, Synthesizer V already provides different nuances by changing vocal styles and tones through Vocal Modes. However, if this “Expression Mode” I imagined is actually what Dreamtonics is going to reveal, I wonder if it could allow users to add various emotions to a voice, perhaps through a control method similar to Vocal Modes or even the current AI Retakes feature.
For example, using the Power mode as an example: the current Power mode helps a voice sound stronger and allows it to project well even in higher ranges. However, I feel that it is still difficult to express something that has power while also carrying a sense of wistfulness or fragility. (Of course, it is possible to lower the Tension parameter or combine it with other types of modes to achieve a similar effect.)
So I think we might see something added that brings more human-like “emotional expression.”
I asked ai about the miracle:
Preparation for the next major engine upgrade: The placement on the official “Coming Soon” subpage indicates that Dreamtonics will shortly introduce a comprehensive update or a new product generation. The community is speculating that this will launch the next stage of AI generation, where manual parameter editing merges even more closely with the intuitive, automatic interpretation of the AI.
haha … 
I think it is related to sound. It sounds really close like in a movie. That would be great. In that case, there is not much to do afterwards, release ready. Now, we still can’t make it sound in a good acoustic environment, even when trying hard.
Wow. That’s your possible thoughts?
Dreamtonics’ teaser features a dodecahedral loudspeaker, an acoustic measurement tool that emits sound at 360 degrees to capture a room’s impulse responses. Paired with the slogan “Human nuance is not a switch”, this visual very likely announces a major evolution in their vocal synthesis technology (particularly for Synthesizer V and choir voicebanks). Concretely, Dreamtonics would abandon binary settings in favor of perfectly continuous variations in emotion and vocal expression, while integrating advanced modeling of spatial acoustics and three-dimensional sound propagation.
For some, teasers set expectations high leading to disappointment.
For others, like me, they’re an annoyance.
So, I’ll wait until you have something definite to say…
Is your reply analysed by AI ? 
No. Only the french to english translation
Looks like a spacial mic or a VR camera. I’m leaning on the 3D sound side.
It’s a dodecahedral loudspeaker.
Something with Dolby Atmos?
I don’t know. Not sure it’ll impact me if it is, or if it’s specific to choirs…
Who knows; maybe they’re axing Windows support next?
