Model · multimodal model
Phonon
Phonon is a multimodal model from Gradium, first covered on 5 November 2026. It is available as open weights you can download and run (licence: Apache 2.0 (English), CC BY-NC 4.0 (multilingual)).
Last updated
Quick facts
- Who makes Phonon?
- Phonon is made by Gradium.
- When was Phonon released?
- The first report of Phonon's release that Digest AI covered was published on 5 November 2026. Hugging Face releases Phonon TTS with on-device speech and open weights →
- What type of model is Phonon?
- Phonon is a multimodal model.
- Are Phonon's weights open?
- Yes. Phonon is released as open weights that can be downloaded and run, under the Apache 2.0 (English), CC BY-NC 4.0 (multilingual) licence.
- Where is Phonon available?
- Phonon is available as open weights that can be downloaded and run.
Taken from the coverage, not from our own testing. A question is left out when none of the reports we read gave the answer. All tracked models →
1 story about Phonon
-
Hugging Face releases Phonon TTS with on-device speech and open weights
Hugging Face launched Phonon, a text-to-speech model designed to run entirely on a user’s device without cloud dependency. The release includes two models: Phonon 31m (Apache 2.0 license, supports English) and Phonon…
2 sources primary sourceUnite.AIHugging Face
Other models from Gradium