I don't know if other people here are interested, but there are some new tools for speech-to-text recognition, that can be used to get the scripts from the audios. Here's one:
https://riverside.fm/transcription
I'm interested in getting scripts from audios because it allows me to change the parts I don't like, combine the parts I like, and translate them to my own language, with a translator and a text-to-speech app. Is there anyone else here interested in the same?
(28 May 2023, 23:15 )princesitanatty Wrote: [ -> ]I don't know if other people here are interested, but there are some new tools for speech-to-text recognition, that can be used to get the scripts from the audios. Here's one: https://riverside.fm/transcription
I'm interested in getting scripts from audios because it allows me to change the parts I don't like, combine the parts I like, and translate them to my own language, with a translator and a text-to-speech app. Is there anyone else here interested in the same?
Oh yes! Thank you. Was looking for a free transcriber since so long. I hope this one works fine, as other free versions available on net are just horrible! I am basically more interested in scripts as i get the idea of whats in the file, before giving it a listen.
(05 Jun 2023, 16:39 )elle Wrote: [ -> ]Oh yes! Thank you. Was looking for a free transcriber since so long. I hope this one works fine, as other free versions available on net are just horrible! I am basically more interested in scripts as i get the idea of whats in the file, before giving it a listen.
It works fine if the audio is more or less clear. I'd like to read the scripts you transcribe, I hope you can share them in this thread.
(08 Jul 2023, 23:41 )Pinkcrowbird Wrote: [ -> ]I used this site for transcription, free and okayish https://converter.app/audio-to-text/
It works great with one voice. And it can distinguish several voices. It was even able to transcribe Samantha Bandler!
(28 May 2023, 23:15 )princesitanatty Wrote: [ -> ]I don't know if other people here are interested, but there are some new tools for speech-to-text recognition, that can be used to get the scripts from the audios. Here's one: https://riverside.fm/transcription
I'm interested in getting scripts from audios because it allows me to change the parts I don't like, combine the parts I like, and translate them to my own language, with a translator and a text-to-speech app. Is there anyone else here interested in the same?
I've found other useful tools.
This one separates vocals from music. It's useful when you find an hypno with voice over music, and you want to remove the music:
https://vocali.se/en
This one removes noise from a voice audio. It can be used to improve the results of the previous one:
https://podcast.adobe.com/enhance
This one allows to automatically remove the silence moments of an audio. It's a portable app, it must be downloaded:
https://www.wavosaur.com/
These tools can be used to prepare the audio for the speech-to-text recognition app, and that's why I talk about them here. But the tools can be also used just to improve audios, so maybe they are also relevant for other threads.