Hugging Face releases on-device TTS model Phonon
Understand the story
On November 5, 2026, the Hugging Face team released Phonon, an on-device text-to-speech model, on its official blog. According to the announcement, the model comes in two sizes, approximately 65 MB and 75 MB, supports five languages — English, French, German, Spanish, and Portuguese — includes over 100 built-in voices, and supports custom voices via voice cloning and voice design. Phonon can run offline on phones, laptops, single-board computers, and in browsers. The blog states that the model tops multiple metrics on the Open TTS Leaderboard. No further developments have been reported so far.
AI overview of reporting · Updated 2 h前
Reporting timeline
Explore different aspects of the story through its reporting.
- Hugging Face BlogSelectedA Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.
The Phonon team reviewed the release of its on-device TTS model Phonon on the Hugging Face blog: the model comes in sizes of about 65 MB and 75 MB, supports English, French, German, Spanish and Portuguese, offers more than 100 built-in voices, supports custom voices via voice cloning and voice design, and can run offline on phones, laptops, single-board computers and in browsers.
Story heat trend
Not enough continuous observations to show a trend yet.