Show HN: Voice cloning for a TTS whose style encoder was never released | Hacker News - But Better

Show HN: Voice cloning for a TTS whose style encoder was never released github.com

Extract voice style embeddings from any WAV for SupertonicTTS — no style encoder needed. - kdrkdrkdr/supertonic.embed

1 points•kdrkdrkdr•5 days ago•0 comments•

#style #voice #encoder #style encoder #whose #never #tts #cloning

0 comments

No comments yet.

Read the full thread on Hacker News →

Related stories

Ask HN: Hypothesis: Cellular providers are deprioritizing voice calls?
Hacker News · 21 points · 6 days ago
Show HN: Giving my inner monologue autocomplete, with my own voicemaximevidal.com
Hacker News · 1 points · 5 days ago
Discourse (open source forums) adds Discord-style voice and video callsmeta.discourse.org
Hacker News · 1 points · 8 days ago
Show HN: Real-time Voice Agent works across apps on Macvoicecursor.ai
Hacker News · 1 points · 1 day ago
Show HN: Selfime, a cassette-style recorder for meditations in your own voiceselfime.com
Hacker News · 1 points · 6 days ago
Show HN: Giving voice agents a voice that adapts to contextgradium.ai
Hacker News · 1 points · 1 day ago