A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.

Phonon is a small, on-device text-to-speech (TTS) model that operates without a network connection, ensuring user privacy. Based on the Pocket TTS lineage and using flow matching, it achieves high-quality voice generation in a compact size, supporting languages like English, French, German, Spanish, and Portuguese. The model's weights are open, with some available under an Apache 2.0 license for commercial use. Phonon excels in performance benchmarks, topping the Hugging Face Open TTS Leaderboard for speed and ranking highly for intelligibility. It is supported by a custom inference framework and is also integrated into the Hugging Face Transformers library for broader accessibility.