Hugging Face released the edge speech model Phonon
The story so far
Hugging Face has released Phonon, a small-scale TTS model that can run on local devices without a server or network, offering two versions of approximately 65 MB and 75 MB, covering English, French, German, Spanish, and Portuguese. Authorization is divided into two categories: Phonon 31m adopts Apache 2.0, which can be used for free, including commercial products; the remaining models are CC BY-NC, which can only be used for free in non-commercial projects. Hugging Face claims that if these models are used to create commercial products, the pricing is calculated based on the number of users rather than the amount of generated speech.
AI-written from the reports · Updated 13 days ago
Coverage timeline
Follow the coverage to see every side of the story.
- Hugging Face BlogFeaturedA Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.
Phonon releases a small TTS model that can run on local devices, without a server and network, offering two versions of about 65 MB and 75 MB, covering English, French, German, Spanish, and Portuguese.