Jump to content

Automatic Voice to Text, Text to voice, saved to audio format.

JensenX
 Share
Posted

I'm looking for an application that will translate my voice to text and then my text back to an unrelated voice.

The goal is to remove personal information from the accent. Choice of words and word pattern will remain.

 

My current ideas:

  • Find an app that natively does this.
  • Find a programming language with the necessary modules to create it (am not fluent in any programming language)
  • Find a voice to text program and do it manually.

Does anyone know anything that could help me achieve my goal?

 

Link to comment
Share on other sites
Link to post
Share on other sites
Posted

Dragon Naturally Speaking  and other applications from that category can convert what you speak to text.

BUT you have to "train it" by speaking at least a few paragraphs, and then you have to speak with a constant rhythm and not very fast and it will still make some typos.

 

As for text to voice, there's lots of programs out there. Amazon has something for a cost (Amazon Polly, 5 million characters each month for free: https://aws.amazon.com/free/machine-learning ), Google has something like that as well : https://cloud.google.com/text-to-speech

here's a Youtube commercial that spams me which advertises a package which produces more natural voice ... but I think it's a cloud solution (as in you pay some money to get a user account on a website and you paste your text there and they give you the sound clip).. of course plays so much i don't even know what it's called but if it pops up I'll try to edit this post to add it.

 

Amazon above also has voice to text, and probably google also, and you could probably also just upload the voice with some blank clip on Youtube and let it produce a subtitle and you get your own speech to text for free.

 

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
Windows also has a built-in voice to text under ease of access.
Link to comment
Share on other sites
Link to post
Share on other sites
Posted
  • Author
36 minutes ago, LWM723 said:

Windows also has a built-in voice to text under ease of access.

I also said I wanted the whole process automated, not just voice to text. Know anything for this?

Link to comment
Share on other sites
Link to post
Share on other sites
Posted

End goal being what exactly? What are you trying to achieve that you couldn't by adding filter that transforms audio in real-time?

 

You mention "removing personal information from accent", while being fine with "choice of words and word pattern remaining". The latter would be much better indicator when identifying person than just accent. Accent and tone only really give few ideas of race/ethnicity, gender and such which are quite generic. Whereas speech patters are how most advanced systems do define person from another.

^^^^ That's my post ^^^^
<-- This is me --- That's your scrollbar -->
vvvv Who's there? vvvv

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
You could just use a voice changer software if that's what your trying to do. Much easier.
Link to comment
Share on other sites
Link to post
Share on other sites
Posted
  • Author
41 minutes ago, LWM723 said:

You could just use a voice changer software if that's what your trying to do. Much easier.

but the voice changer software will retain some of the original voice. I'm not yet comfortable with what I've managed with it. Spent a lot of time and besides pitch and a few effects it didn't seem good enough. I also didn't find a good vocoder which would have been alright.

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
  • Author
1 hour ago, LogicalDrm said:

End goal being what exactly? What are you trying to achieve that you couldn't by adding filter that transforms audio in real-time?

 

You mention "removing personal information from accent", while being fine with "choice of words and word pattern remaining". The latter would be much better indicator when identifying person than just accent. Accent and tone only really give few ideas of race/ethnicity, gender and such which are quite generic. Whereas speech patters are how most advanced systems do define person from another.

This is news to me. Do you have sources where I can read more on this?

The goal is to speak anonymously but with something more lively and convenient than text to speech synth

Link to comment
Share on other sites
Link to post
Share on other sites
Posted
10 hours ago, JensenX said:

This is news to me. Do you have sources where I can read more on this?

The goal is to speak anonymously but with something more lively and convenient than text to speech synth

You haven't watched any documentaries ever? Or Twitch or YT? Anyway, https://appuals.com/the-5-best-voice-changer-software-to-use/

Pretty much that. As in tools many streamers and content creators use for fun and pranks.

^^^^ That's my post ^^^^
<-- This is me --- That's your scrollbar -->
vvvv Who's there? vvvv

Link to comment
Share on other sites
Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now
 Share
Go to topic listing Programs, Apps and Websites

×