Peaked at #3 Now #4
Gradium open-sources Phonon speech models
Gradium open-sources Phonon, a suite of sub-50M-parameter TTS models, with Phonon-31m under Apache 2.0.
Key points
- GradiumAI open-sources Phonon, a suite of TTS models under 50m parameters, with the broadest inference support to date.
- Phonon-31m is available under Apache 2.0.
- GradiumAI says its English models set a new standard for naturalness and accuracy at their size, and calls the multilingual step change in speech quality over previous on-device models across five languages the real breakthrough.
Key points and the reaction summary are written by AI from the posts on this page. Check the original post. How we use AI
Original post
Top replies on X
Reaction on X: Replies were largely positive, with users calling it "open source ftw," offering congratulations, and saying they plan to use it in an upcoming app. One user asked how it handles Latin American Spanish, particularly Rioplatense. The original poster replied, adding that the English models set a new standard at their size while the multilingual step change is the real breakthrough.
Sign in to see 5 top replies from X
From @GradiumAI, @thisdudelikesAI, @eudtoxic and others. Spam removed, with English and Chinese translations.
Discussion 0
Sign up Sign in to join the discussion
No comments yet. Start the conversation.