Audio & Voice
Phonon
Gradium's open on-device text-to-speech models at 31M and 40M parameters.
💡 The Apache-2.0 English model is 64 MB and starts speaking in milliseconds on a laptop CPU.
Audio & Voice
Gradium's open on-device text-to-speech models at 31M and 40M parameters.
💡 The Apache-2.0 English model is 64 MB and starts speaking in milliseconds on a laptop CPU.
One short email when the digest goes out.