A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.
Hugging Face released Phonon, a compact on-device text-to-speech model that runs locally without internet. Available in two sizes with Apache 2.0 and non-commercial licenses, it supports five languages and custom voices. Phonon tops the Open TTS Leaderboard in intelligibility for German and Spanish and leads CPU streaming speed benchmarks.
Key signals
- 01On-device TTS model runs locally without network connectivity
- 02Tops leaderboard in German/Spanish intelligibility and CPU streaming speed
- 03Available in Transformers with new ptts framework supporting 10+ backends
A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks., published by Hugging Face.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Hugging Face
Read the full story at the source: huggingface.co.
Curated automatically from Hugging Face. Infrenic News links to the original publisher and does not republish its content.
Daily briefing
Get the next briefing before everyone else.
Five AI stories, five minutes, every morning.
