[nine_k]

Does anybody find it funny that sci-fi movies have to heavily distort "robot voices" to make them sound "convincingly robotic"? A robotic, explicitly non-natural voice would be perfectly acceptable, and even desirable, in many situations. I don't expect a smart toaster to talk like a BBC host; it'd be enough is the speech if easy to recognize.

[userbinator]

A robotic, explicitly non-natural voice would be perfectly acceptable, and even desirable, in many situations[...]it'd be enough is the speech if easy to recognize.

We've had formant synths for several decades, and they're perfectly understandable and require a tiny amount of computing power, but people tend not to want to listen to them:

https://en.wikipedia.org/wiki/Software_Automatic_Mouth

https://simulationcorner.net/index.php?page=sam (try it yourself to hear what it sounds like)

[miki123211]

SAM and the way it works is not what people typically associate with the term "formant synthesizer."

DECtalk[1,2] would be a much better example, that's as formant as you get.

[1] https://en.wikipedia.org/wiki/DECtalk [2] https://webspeak.terminal.ink

[saretup]

Well, this one is a bit too jarring to the ears.

[rixed]

But there is no latency, as opposed to KittenTTS, so it certainly has its applications too.

[cess11]

Try this demo, which has more knobs:

https://discordier.github.io/sam/

[actionfromafar]

I think it's charming

[boobsbr]

Huh, now I know what Airdorf used in Faith: Unholy Trinity.

[tapper]

Yeah blind people love eloquence

[roywiggins]

This one is at least an interesting idea: https://genderlessvoice.com/

[cosmojg]

The voice sounds great! I find it quite aesthetically pleasing, but it's far from genderless.

[a96]

So, what's the gender?

[dang]

Meet Q, a Genderless Voice - https://news.ycombinator.com/item?id=19505835 - March 2019 (235 comments)

[cyberax]

It doesn't sound genderless.

[degamad]

Interesting concept, but why is that site filled with Top X blogspam?

[pbronez]

The YouTube video [1] was published in 2019. The Blog spam posts range from Nov 2022 to July 2023.

Other than the video, the only relevant content is on the about page [2]. It says the voice is a collaboration between 5 different entities, including advocacy groups, marketing firms and a music producer.

The video is the only example of the voice in use. There is no API, weights, SDK, etc.

I suspect this was a one-off marketing stunt sponsored by Copenhagen pride before the pandemic. The initial reaction was strong enough that a couple years they were still getting a small but steady flow of traffic. One of the involved marketing firms decided to monetize the asset and defaced it with blog spam.

[1] https://www.youtube.com/watch?v=lvv6zYOQqm0

[2] https://genderlessvoice.com/about/

[pbronez]

Huh. Sounds perfectly intelligible and definitively artificial. Feels weakly feminine to me, but only because I was primed to think about gender from the branding.

It’s a good choice for a robot voice. It’s easier to understand than the formant synths or deliberately distorted human voices. The genderless aspect is alien enough to avoid the uncanny valley. You intuitively know you’re dealing with something a little different.

[qmr]

Thanks, I hate it.

[mfro]

In the Culture novels, Iain Banks imagines that we would become uncomfortable with the uncanny realism of transmitted voices / holograms, and intentionally include some level of distortion to indicate you're speaking to an image

[incone123]

Depends on the movie. Ash and Bishop in the Alien franchise sound human until there's a dramatic reason to sound more 'robotic'.

I agree with your wider point. I use Google TTS with Moon+Reader all the time (I tried audio books read by real humans but I prefer the consistency of TTS)

[regularfry]

Slightly different there because it's important in both cases that Ripley (and we) can't tell they're androids until it's explicitly uncovered. The whole point is that they're not presented as artificial. Same in Blade Runner: "more human than human". You don't have a film without the ambiguity there.

[incone123]

You're right. I should have used Marvin from Hitchhiker's Guide as an example instead. There's very light processing on his speech.

[Twirrim]

> I don't expect a smart toaster to talk like a BBC host;

Well sure, the BBC have already established that it's supposed to sound like a brit doing an impersonation of an American: https://www.youtube.com/watch?v=LRq_SAuQDec

[looperhacks]

I remember that the novelization of the fifth element describes that the cops are taught to speak as robotic as possible when using speakers for some reason. Always found the idea weird that someone would _want_ that

[addandsubtract]

If you're on a Mac, you can type "say [thing to say]" into your terminal.

[msgodel]

I personally prefer the older synthetic voices for TTS when the text is coming from software or a language model.