NHacker Next
  • new
  • past
  • show
  • ask
  • show
  • jobs
  • submit
Spark-TTS: Text-2-Speech Model Single-Stream Decoupled Tokens [pdf] (arxiv.org)
mike978 19 hours ago [-]
smusamashah 9 hours ago [-]
The voices with Chinese origin when generated as English samples do sound like a Chinese person speaking English. It is very interesting.
vessenes 12 hours ago [-]
This is really quite good at sounding like Donald, especially for the first half of the audio. I’ll probably play around with this for a bit; it’s. It clear to me how much variation you can get in voice in latent space. Anyway it looks to be a very high quality (at least) short form tts engine with open weights so thanks team!
fdafds 14 hours ago [-]
[flagged]
Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Rendered at 14:20:59 GMT+0000 (UTC) with Wasmer Edge.