Skip to content
English

Switch theme

// AI news · 2026-11-05 · Hugging Face Blog

Hugging Face Launches On-Device TTS Model Phonon

Hugging Face launched Phonon, a high-quality on-device text-to-speech model that runs locally without network or server access.

Published 2026-11-05 08:00 (Beijing time)Source Hugging Face BlogAuto-summarised, fact-checked against source

01Summary

Built on Pocket TTS lineage using flow matching, it achieves strong performance in intelligibility and speed across five languages. It ranks first in German and Spanish on the Hugging Face Open TTS Leaderboard and leads in time-to-first audio on CPU streaming benchmarks. The model is available via Hugging Face Transformers 5.21 and supports multiple hardware backends including CPU, GPU, and NPU.

Summarised from the original article by an open-source model, then checked automatically: every number and English name must appear in the source. The original article is authoritative.

02Key points

03Source

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

Hugging Face Blog · published 2026-11-05 08:00 Beijing time

05Related news

From AIMap AI news: collected from 1,100+ official and media sources. Summaries only restate the original article; follow the link for the full story. All stories of 2026-11-05 · Archive by date · All AI news · Today

Data updated: AI news(UTC+8)