Gradium releases Phonon text-to-speech models that run on-device
Overview
Gradium releases Phonon, a set of text-to-speech models that run on-device without a server or network connection, according to a Hugging Face blog post by Gradium.
Phonon 31m for English is licensed under Apache 2.0, so it can be used for free, including in commercial products. Phonon 40m covers five languages under CC BY-NC, which allows only non-commercial use. Gradium says commercial use of the non-commercial models is priced by number of users, not by the amount of speech generated. Gradium also reports that Phonon ranks first in German and Spanish on intelligibility on the Hugging Face Open TTS Leaderboard and leads on time-to-first audio, with Transformers support from v5.21.
Written by AI from the articles below · updated Nov 5, 6:06 AM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Hugging Face BlogOfficialPickGradium's Phonon TTS launch runs speech models on-device with open weights
AIGradium says its Phonon text-to-speech models run on-device without a server or network connection. Phonon 31m for English is Apache 2.0 and usable commercially, while Phonon 40m covers five languages under a non-commercial license. The post reports Phonon ranks first in German and Spanish on intelligibility on the Hugging Face Open TTS Leaderboard and leads on time-to-first audio, with Transformers support from v5.21.
Heat Trend
Not enough continuous observations to show a trend yet.