I honestly think the accent is adorable! I knew Maki wasn't going to be aimed at Westerners anyway, but I still liked what I heard in those demos, that one bizarre sentence aside. It's accented, but not really difficult to understand.
Honestly, even the nonsense sentences are growing on me. She sounds like she’s stoned off her gourd and trying to be philosophical. I just keep imagining Yukari in the background, nodding and telling her that yes Maki, that makes perfect sense, you’re so enlightened.I honestly think the accent is adorable! I knew Maki wasn't going to be aimed at Westerners anyway, but I still liked what I heard in those demos, that one bizarre sentence aside. It's accented, but not really difficult to understand.
No one was upset with you just because you simply don't like Maki, you don't need to justify not liking her to us because you have full right to hold that opinion.I wrote an apology on Twitter for writing my humble opinion in an angry tone. I shouldn't have written it so passionately/assumed people would agree. But I have legitimate reasons Maki is not up to par for me personally.
I use TTS many hours a week, I can not read long passages without it in English or Japanese. I own CeVIO, VOICEROID, and A.I.VOICE for Japanese and use Microsoft TTS for English. When Maki got announced, I assumed she would be of quality similar to what AI Inc has to offer (on this page, scroll down for audio clips 様々な言語での音声合成を可能にします。 AITalk International® )
It was dumb to assume that I would get a certain quality, but at the same time, I REALLY wanted a TTS of a character voice that could narrate to me instead of Microsoft Mark.
When I use the CeVIO/VOICEROID/A.I.VOICE banks, I input the text and do not have to edit it much. It's just type and export, I do not want to tune speech that is supposed to sound natural by default, especially through AI. I don't have to tweak the voices most of the time in VOICEROID/A.I.VOICE and I perceive Maki as needing excessive tweaking that isn't worth the effort based on the sheer amount of TTS narration I need per week. I do not appreciate being told by people (ex: Twitter) that I am using TTS wrong by assuming I could've used it for educational narration when they think it's clearly meant only for skits or that I'm "using it wrong" when I do spend many, many hours listening to TTS and I know what I want/need from a voice bank.
Also, I legitimately thought that Maki was not 100% understandable but people got really angry at me because they said they can understand her fully. For me, there is no purpose in owning a voice bank I can not understand just by listening (because I can't pay attention/repeatedly lose my place while trying to follow along to text, I NEED to be able to understand the voice without seeing the words). She might be the perfect character voice for some people, but I was planning on having a voice to help me do my daily function of reading + use for my educational website. I got worked up because Maki isn't how I imagined she would be based on my experience with other TTS.
Lastly, I am very uncomfortable with people accusing me of disliking Japanese accents. I have been speaking in Japanese and English to bilingual Japanese users on Skype since 2008. I am used to accents and like it when people speak English with whatever ability they have. But this is a product and not a person per-say in my humble opinion. My criticisms are purely because of my perceived time to edit her voice and having some words I can not understand being said, it's about my accessibility.
We won't know her true quality until a demo page comes out and we can purchase her. And I think we need to realize that TTS has fans that are both people collecting unique/novelty voices as well as people needing TTS for actual accessibility. It's like how some English song banks are hard to use due to wonked up phonemes even if it's a native voice bank or not.
I get that you use TTS for accessibility purposes, I do the same as well when I´m unable to read certain texts. I'm also not sure where you're getting that we're accusing of you anything? Especially me since that's the post you're quoting? All I'm saying is that Maki really isn't the TTS you want to go for or even complain about when Maki, even looking from a product standpoint, is made one purpose over another. It's clearly not aimed at native English speakers for native English use and that was the point I was trying to make. I'm sorry if I made you feeling attacked or anything of the sort, that was not my intention.I wrote an apology on Twitter for writing my humble opinion in an angry tone. I shouldn't have written it so passionately/assumed people would agree. But I have legitimate reasons Maki is not up to par for me personally.
I use TTS many hours a week, I can not read long passages without it in English or Japanese. I own CeVIO, VOICEROID, and A.I.VOICE for Japanese and use Microsoft TTS for English. When Maki got announced, I assumed she would be of quality similar to what AI Inc has to offer (on this page, scroll down for audio clips 様々な言語での音声合成を可能にします。 AITalk International® )
It was dumb to assume that I would get a certain quality, but at the same time, I REALLY wanted a TTS of a character voice that could narrate to me instead of Microsoft Mark.
When I use the CeVIO/VOICEROID/A.I.VOICE banks, I input the text and do not have to edit it much. It's just type and export, I do not want to tune speech that is supposed to sound natural by default, especially through AI. I don't have to tweak the voices most of the time in VOICEROID/A.I.VOICE and I perceive Maki as needing excessive tweaking that isn't worth the effort based on the sheer amount of TTS narration I need per week. I do not appreciate being told by people (ex: Twitter) that I am using TTS wrong by assuming I could've used it for educational narration when they think it's clearly meant only for skits or that I'm "using it wrong" when I do spend many, many hours listening to TTS and I know what I want/need from a voice bank.
Also, I legitimately thought that Maki was not 100% understandable but people got really angry at me because they said they can understand her fully. For me, there is no purpose in owning a voice bank I can not understand just by listening (because I can't pay attention/repeatedly lose my place while trying to follow along to text, I NEED to be able to understand the voice without seeing the words). She might be the perfect character voice for some people, but I was planning on having a voice to help me do my daily function of reading + use for my educational website. I got worked up because Maki isn't how I imagined she would be based on my experience with other TTS.
Lastly, I am very uncomfortable with people accusing me of disliking Japanese accents. I have been speaking in Japanese and English to bilingual Japanese users on Skype since 2008. I am used to accents and like it when people speak English with whatever ability they have. But this is a product and not a person per-say in my humble opinion. My criticisms are purely because of my perceived time to edit her voice and having some words I can not understand being said, it's about my accessibility.
We won't know her true quality until a demo page comes out and we can purchase her. And I think we need to realize that TTS has fans that are both people collecting unique/novelty voices as well as people needing TTS for actual accessibility. It's like how some English song banks are hard to use due to wonked up phonemes even if it's a native voice bank or not.
I’ve... I’ve heard many complaints and criticisms towards Maghni AI, and that’s not at all one of them. Or if it is, it’s not at all on a large scale. Criticisms towards Maghni AI tend to be more focused on their general lack of transparency and their hyperfocus on all the future plans they have when they don’t even have a functioning engine and VB built yet. I understand you’re upset about people’s reactions and MAI is close to your heart, but I feel like this is grasping at straws. Maki’s issues and market and MAI’s aren’t the same and shouldn’t be compared in the same breath.I will say one thing, though, I find it highly ironic how people are okay with Maki English but were flipping their lids about the possibility that Maghni AI voice banks might be voiced by non-natives.
When I was on the team, we literally had meetings (with an S) about the native speaker criticism. We would read ALL complaints/compliments on various websites. It happened within the first month of announcements but gradually shifted to be about transparency/have too many over-the-top ideas in current months. So no, I don't think I'm grasping at straws when I compare the reaction by English speakers about vocal synth product pronunciation issues.I’ve... I’ve heard many complaints and criticisms towards Maghni AI, and that’s not at all one of them. Or if it is, it’s not at all on a large scale.
It can be used, no one will stop you, doesn't change that she's made for specific niche.Also, I checked back at Techno-Speech's website and it touts the fact that their TTS can be used for game/anime voice acting, announcements and Let's Plays, medical use, so I realized that yes, I am salty that I got quote tweeted and PMed about being dumb and wrong for assuming the product would work for those things instead of just skit videos.
There's a difference between the TTS engine and the voice that is using it. Vocaloid can be used for movie soundtracks, games, teaching, etc. but you're not going to be seeing people complaining about Gachapoid and asking why he doesn't have the quality of VY1 or why he's more limited in terms of usage compared to other voices. That's just not how it works. Some companies release general use products, some release for niches; and Maki is definitely for the niche.Also, I checked back at Techno-Speech's website and it touts the fact that their TTS can be used for game/anime voice acting, announcements and Let's Plays, medical use, so I realized that yes, I am salty that I got quote tweeted and PMed about being dumb and wrong for assuming the product would work for those things instead of just skit videos.
Not to be contrarian, but I have definitely seen this complaint/concern, esp after the MAI staff suggested that their VAs could make a bank in any language possible because of the scripts they were using.I’ve... I’ve heard many complaints and criticisms towards Maghni AI, and that’s not at all one of them. Or if it is, it’s not at all on a large scale. Criticisms towards Maghni AI tend to be more focused on their general lack of transparency and their hyperfocus on all the future plans they have when they don’t even have a functioning engine and VB built yet. I understand you’re upset about people’s reactions and MAI is close to your heart, but I feel like this is grasping at straws. Maki’s issues and market and MAI’s aren’t the same and shouldn’t be compared in the same breath.
Ah, now THAT I can see! Forgive me. I tend to stay faaaaaaaar away from the mess that is VocaTwitter, so I tend to have a limited perspective.Not to be contrarian, but I have definitely seen this complaint/concern, esp after the MAI staff suggested that their VAs could make a bank in any language possible because of the scripts they were using.