You should really see what happens when you click reject on their terms and conditions prompt.
Deep-learning text-to-speech tool for generating voices of various characters
61–70 of 88 posts
Re: Deep-learning text-to-speech tool for generating voices of various characters
#62I'm rarely impressed by demos like this. This is a clear exception.
Not only that, but the creator seems cool and down to earth. Thanks for sharing, this is incredible work.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#63Really impressive. Do you plan to implement an API like Amazon, Google that lets you generate TTS for price?
I too think that this has potential as a cloud TTS service. However that does open up all the moral and legal cans of worms around this. I could imagine some of the voice actresses not being very happy about somebody else commercializing their voice without their consent.
The obvious way to get around this is to keep this as the showcase and to pay some people to add their voices to the paid version. I imagine this would sell just based on being decent TTS with a wide range of voices, even when people don't know the voices offered.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#64As Alexa and Siri have improved over the last couple years and gotten a more human voice, it has been interesting observing my young children (1-4) interact with such devices.
There is definitely a sense of ‘who is that’ coming from their little minds that they are sometimes quite perplexed about. ‘It’s a computer’ is starting to feel like a cop-out answer as these things improve...
Re: Deep-learning text-to-speech tool for generating voices of various characters
#65seriously fuck anyone that is putting in forced time delays on their terms, how about you let me read what it is you are doing before requiring shit like this.
If you don't agree with the terms, including how they are presented to you, you can always reject them and leave the site.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#66The fact that you included Chell as a voice choice (and 'generated' a null audio clip to boot) earns a chuckle. The quality of the voices across the board earns wide eyes and an eyebrow raise. Thanks for sharing this, it's remarkable work.
GLaDOS hahahaha this is just... perfect.
Stanley Parable Narrator funny you should mention this.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#67It’s incredible how little data is required for amazing output! Only a couple of minutes of talking needed.
You can find a couple of minutes of taking of anyone, so the security implications are huge!
Re: Deep-learning text-to-speech tool for generating voices of various characters
#68From the about section: > How much does maintaining the servers cost? > It depends on the amount of traffic, but the minimum baseline is around several thousands of US dollars every month. This is expected as inference is very GPU intensive and a sufficient number of instances need to be spun up to handle thousands of requests coming in every minute. Everything is paid out of pocket. Wow, impressive commitment for so…
The price of GPU inference can be brutal, but there's a lot you can do on the infra side to improve it:
- Spot instances
- Aggressive autoscaling
- Micro batching
Can reduce inference compute spend by huge amounts (90% is not uncommon). ML, especially anything involving realtime inference, is an area where effective platform engineering makes a ridiculous difference even in the earliest days.
Source: I help maintain open source ML infra for GPU inference and think about compute spend way too much https://github.com/cortexlabs/cortex
Re: Deep-learning text-to-speech tool for generating voices of various characters
#69The security implications of this kind of tech are scary. Going forward it will become really easy to reproduce the voice of anyone! It seems not a lot of training data is required to achieve reasonable results (e.g. Spong Bob is just 27min of voice, Half Life Black Mesa Announcer is just 1.9min!!). This stuff could be easily leveraged for scams and deep fakes (along with deep learning models that could also tweak li…
These kinds of discussions are common with articles about deep fake video and audio. While I do not disagree with your point, here are two quick thoughts: - We have had perfect image manipulation capabilities for quite some time now. We have had written text manipulation capabilities for hundreds of years. - People will continue to believe what they believe, whether there is deep fake video and audio or not.
Agree with you. Hopefully people are more and more aware that they cannot trust anything out there. We are soon reaching a point where we can make anyone say anything we want, including in audio and video format.
Re: Deep-learning text-to-speech tool for generating voices of various characters
#70From the about section: > How much does maintaining the servers cost? > It depends on the amount of traffic, but the minimum baseline is around several thousands of US dollars every month. This is expected as inference is very GPU intensive and a sufficient number of instances need to be spun up to handle thousands of requests coming in every minute. Everything is paid out of pocket. Wow, impressive commitment for so…
Out of curiosity, as I have no visibility about the infra actually required- but at that cost, would it not be easier to just have a machine under a desk somewhere?