Play.ht Reviews

Every Noice at Once Reviews

Play.ht mentions (64)

• [D] What offline TTS Model is good enough for a realistic real-time task?

  There aren't really any models that produce realistic real-time voice. I'd recommend ElevenLabs or play.ht, sadly these seem to be the only useable options for now. Source: 7 months ago

• Where can I find an online resource of voice cloning?

  I've used play.ht before. Very easy to use. Source: 12 months ago

• Voice generation AI (TTS)

  Does anyone know what they are using and if its possible to get it and run it locally? I have a lot of text to voice (1 500 000 characters, 300 000 words) so using services as elevenlabs or play.ht would be pretty expensive. The quality is secondary to it being reasonably fast (got a 2060 super, dont want to run it for 4 months straight to generate all this dialogue). Source: almost 1 year ago

• Best AI Voice for Audio Books - Play.ht?

  My experience with play.ht wasn't positive, had way better luck paying the eleven labs premium. Source: about 1 year ago

• Best AI Voice for Audio Books - Play.ht?

  (The biggest problem I have with play.ht is it won't do some things because "Your content violates our standards" and that is for "fight scenes" written over 100 years ago). Source: about 1 year ago

Every Noice at Once mentions (422)

• When do we stop finding new music?

  I see this in https://everynoise.com/#updates > 2024-01-05 status update: With my layoff from Spotify on 2023-12-04, I lost the internal data-access required for ongoing updates to many parts of this site. Most of this, as a result, is now a static snapshot of what, for now, will be the final state from the site's 10-year history and evolution, hosted on my own server. Some pieces may get disabled and reenabled... - Source: Hacker News / 2 months ago

• Spotify launches personalized AI playlists that you can build using prompts

  Anyone aware of a similar feature for foobar2000? I have an extensive library mostly tagged from Discogs, including release IDs. In theory, this should be sufficient to cluster music by genres, pull similar releases from Discogs "similar" feature and correlate data from https://everynoise.com. Obviously, in case of album mixed genres things will mix up, but I'm not sure there's a model that can correlate existing... - Source: Hacker News / 3 months ago

• Displaying Content as a Graph

  The article mentions Glenn McDonald's musical genre page (https://everynoise.com/, no longer refreshing with new Spotify data) as an example of a flexible graph-like exploration format, without being burdened by explicit connections. The author also has a thorough description of pros and cons of the general concept. - Source: Hacker News / 6 months ago

• The Beginning of the Past

  This is from Glenn McDonald's blog, founder of "Every Noise at Once". He was laid off from Spotify (discussed here briefly [0]) --- https://everynoise.com/ is now in "archival copy" mode [1][2]. Super sad to read / see this. [0] https://news.ycombinator.com/item?id=38650917 [2] https://twitter.com/EveryNoise/status/1736086849339244935. - Source: Hacker News / 7 months ago

• [OC] Exploring my world of music in 7 years of listening data

  Data exported using: https://benjaminbenben.com/lastfm-to-csv/ Album art compiled using: https://www.neverendingchartrendering.org/ Genre data compiled using: http://organizeyourmusic.playlistmachinery.com/# https://everynoise.com/ https://www.tunemymusic.com/transfer Gender, year and country of origin information manually compiled using Last.fm and wikipedia. Data analysis done in excel and image created in GIMP. Source: 7 months ago