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.
More from Multimodal
- Dense instance segmentation via Muse Wonder + SAM 3.1 on Meta's Model API — nikhilaravi · 2026-10-26
- LichtFeld Studio v0.5.4.3 ships community-built SteadySplats, POPSpa and Voxelization — janusch_patas · 2026-10-26
- One prompt to a 2-3 min narrated short: hands-on test of Antigravity video generation — AI_Andrew · 2026-10-26
- Creator makes 10,564-frame animated short entirely with Gemini toolchain — AI_Andrew · 2026-10-26
- FLUX.3 Klein step-distilled to 4-8 steps with CFG baked in — Fit-Structure-6489 · 2026-10-26
- ostris pre-training "Primal VAE": 1-channel latents match modern 8x VAEs via patching — ostrisai · 2026-10-26