Audio8 Open-Sources On-Device Audio Models From 0.1B to 3B for ASR and TTS

alexcovo_eth · x · 2026-09-08

Samuel Zeng's team has open-sourced multiple generations of on-device audio models via Audio8 over the past two months. The portfolio includes ASR models at 0.1B, 0.3B, 0.6B, and 3B, plus TTS models at 0.1B, 0.3B, and 0.6B — all designed for local inference on phones, PCs, and resource-constrained devices.

Original post →

More from Multimodal

Multimodal channel →