Audio8 TTS Preview 0.1B — now on Hugging Face as ONNX INT8
~100M params · 11 languages · zero-shot voice cloning
Runs on CPU only (~0.4 GB RAM) — no PyTorch, no CUDA
44.1 kHz · OpenAI-compatible API · Apache 2.0
Try it 👇
#TTS# #VoiceCloning# #ONNX# #OpenSource#
audio.cpp is basically Ollama for audio: one native C++ runtime for local voice cloning, TTS, STT and more.
I tested it on Apple Silicon. No cloud, no Python at inference.
Audio clips released by the Oversight Project of former-President Joe Biden’s conversations with his biographer, Mark Lewis Zwonitzer, appear to support what former Special Counsel Robert Hur found in his 2024 report: Biden disclosed classified material, was forgetful and continued to possess classified material after leaving his post as vice president.
Audio of then-14-year-old school shooter Colt Gray's confession played in court, where he told police after the shooting that he experienced auditory issues, including constant "whispering."
"I couldn't wait. I told him to hide his guns, and he did, but I don't know... I found them."
Gray has pleaded guilty to all 55 counts. He killed two teachers and two students, and injured others.
Audiomob uses Gemini Enterprise Agent Platform, BigQuery, GKE, and more to deliver AI-powered audio ad generation across 18 languages.
The results: 20% revenue uplift for developers, 5-7% higher CTR for advertisers, and over 90% listen-through rates for brands ↓
Audio version of our newest @OriginsProject podcast with Nobel Laureate Alvin Roth on his new book, Moral Economics, is live now on all podcast sites, and on our Critical Mass substack channel. Link :