Good text-to-speech systems
- KVRAF
- Topic Starter
- 1745 posts since 2 Jul, 2018
I need some spoken texts for a tutorial video, but am too lazy to do an own recording.
Do you known websites where you can synthesize spoken text in good quality?
Thanks
Do you known websites where you can synthesize spoken text in good quality?
Thanks
- KVRAF
- 8815 posts since 6 Jan, 2017 from Outer Space
Murf.ai
Deep networks are exploding. Its like in the first days of the internet…
Deep networks are exploding. Its like in the first days of the internet…
-
- KVRAF
- 15508 posts since 13 Oct, 2009
None of them that are good quality will be free. Also, personally, I find that takes longer to write speech than to just perform it. To be clear, when it's something that I know what I'm talking about, it's usually less work to just outline the tutorial then record it live than to try and figure out exactly what I would say and type that up. You can just use read aloud in word to figure out what you want to say in your tutorial, it's not super realistic, but it's good enough to get you started.
-
- KVRist
- 488 posts since 15 Jun, 2018
Last edited by jules99 on Wed Feb 08, 2023 1:29 pm, edited 1 time in total.
- KVRian
- 959 posts since 20 Oct, 2018
Balabolka - https://balabolka.en.softonic.com/download
-
- KVRian
- 624 posts since 12 Sep, 2007
-
- KVRAF
- 10984 posts since 19 Jun, 2008 from Seattle
...
Last edited by Shabdahbriah on Wed Feb 08, 2023 2:32 pm, edited 1 time in total.
I'm not a musician, but I've designed sounds that others use to make music. http://soundcloud.com/obsidiananvil
-
- KVRAF
- 10984 posts since 19 Jun, 2008 from Seattle
'change the speed'Dirk Diggler wrote: ↑Wed Feb 08, 2023 1:05 pm https://azure.microsoft.com/en-us/produ ... /#overview
(not bad actually)
Aside from that, I wish I could remember where I put my notes/links on these things, and the stand-out ones I've found, to help you out. The newer AI modeling is really fascinating how far it (and the tech in general) has come in the past couple of years. I had one of those mellifluous/melodious "announcer" broadcaster voices from (like) age 13, and did many hundreds of radio/TV voice talent things way back, but having lost that (voice) for the most part, I've been considering recording my copy, and doing a voice-to-text, then text to voice using AI. It's worthwhile (and interesting) doing some research.
Last edited by Shabdahbriah on Wed Feb 08, 2023 3:02 pm, edited 1 time in total.
I'm not a musician, but I've designed sounds that others use to make music. http://soundcloud.com/obsidiananvil
-
- KVRAF
- 10984 posts since 19 Jun, 2008 from Seattle
That's quite impressive, indeed. I can't post the mp3, but used this copy:jules99 wrote: ↑Wed Feb 08, 2023 8:45 am https://beta.elevenlabs.io/speech-synthesis
This right here gets you very convincing results.
"I'd really like to explain this to you but I'm all out of chalk, and crayons" and the pronunciation, inflection, emphasis, tonality, etc were remarkable with several of the voices.
I'm not a musician, but I've designed sounds that others use to make music. http://soundcloud.com/obsidiananvil
-
- addled muppet weed
- 105553 posts since 26 Jan, 2003 from through the looking glass
voice to text.Shabdahbriah wrote: ↑Wed Feb 08, 2023 2:31 pm I've been considering recording my copy, and doing a voice-to-text, then text to voice using AI. It's worthwhile (and interesting) doing some research.
google translate, from eng to chi to fre to ger to chi to eng.
text to speech.
- KVRian
- 959 posts since 20 Oct, 2018
Here's some more voices:
http://www.zero2000.com/free-text-to-sp ... oices.html
http://www.zero2000.com/free-text-to-sp ... oices.html
-
- KVRAF
- 10984 posts since 19 Jun, 2008 from Seattle
That would be fun. I'm thinkin' more like Sadhguru does eurorack.vurt wrote: ↑Wed Feb 08, 2023 3:08 pmvoice to text.Shabdahbriah wrote: ↑Wed Feb 08, 2023 2:31 pm I've been considering recording my copy, and doing a voice-to-text, then text to voice using AI. It's worthwhile (and interesting) doing some research.
google translate, from eng to chi to fre to ger to chi to eng.
text to speech.
I'm not a musician, but I've designed sounds that others use to make music. http://soundcloud.com/obsidiananvil
-
- KVRist
- 146 posts since 4 Dec, 2014 from Ukraine, Germany->Munich
-
- KVRAF
- 3488 posts since 1 Sep, 2016
-
gentleclockdivider gentleclockdivider https://www.kvraudio.com/forum/memberlist.php?mode=viewprofile&u=203660
- KVRAF
- 6076 posts since 22 Mar, 2009 from gent
Support a fellow developer like ‘plogue’ and buy chipspeechMarkus Krause wrote: ↑Wed Feb 08, 2023 5:56 am I need some spoken texts for a tutorial video, but am too lazy to do an own recording.
Do you known websites where you can synthesize spoken text in good quality?
Thanks
Eyeball exchanging
Soul calibrating ..frequencies
Soul calibrating ..frequencies