Skip to main content
18 events
when toggle format what by license comment
Nov 19, 2023 at 21:21 history bounty ended emonigma
S Nov 15, 2023 at 11:17 history suggested emonigma CC BY-SA 4.0
added details
Nov 14, 2023 at 19:43 vote accept emonigma
Nov 14, 2023 at 19:43 comment added emonigma Thanks! I didn't try the first, Neural Voice Cloning with a Few Samples. I tried the second, Unet-TTS, out-of-the-box and it fails with ERROR: Could not find a version that satisfies the requirement tensorflow-gpu==2.6.0. I tested ElevenLabs and liked the results very much, but unfortunately they don't have my target language. BeyondWords seems very good, but they require 2-8 hours of audio, which is infeasible in my case. So, if my use case had the luck of falling into ElevenLabs' language, I would use that, and so I'm accepting the answer.
Nov 14, 2023 at 19:39 review Suggested edits
S Nov 15, 2023 at 11:17
Mar 20, 2023 at 10:06 history edited Hans-Peter Schrei CC BY-SA 4.0
Added commercial information about voice cloning in ElevenLabs.
Mar 20, 2023 at 9:43 history edited Hans-Peter Schrei CC BY-SA 4.0
Fixed reference
Mar 20, 2023 at 8:33 history edited Hans-Peter Schrei CC BY-SA 4.0
added 821 characters in body
Mar 20, 2023 at 8:08 history edited Hans-Peter Schrei CC BY-SA 4.0
Fixed typo
S Mar 20, 2023 at 8:06 history suggested emonigma CC BY-SA 4.0
added details on BeyondWords.io
Mar 20, 2023 at 8:03 review Suggested edits
S Mar 20, 2023 at 8:06
S Mar 19, 2023 at 23:19 review First answers
Mar 20, 2023 at 16:57
S Mar 19, 2023 at 23:19 history edited Hans-Peter Schrei CC BY-SA 4.0
Removed existing answer, added new project
Mar 19, 2023 at 23:09 history undeleted Hans-Peter Schrei
Mar 19, 2023 at 23:09 history edited Hans-Peter Schrei CC BY-SA 4.0
Removed existing answer, added new project
Mar 19, 2023 at 23:03 history deleted Hans-Peter Schrei via Vote
S Mar 19, 2023 at 23:03 review First answers
Mar 19, 2023 at 23:07
S Mar 19, 2023 at 23:03 history answered Hans-Peter Schrei CC BY-SA 4.0