Building Up a Rhythmic Spanish Voice With LLMs and TTS
AI and I
0 follower
Follow
1
12 views • 4 months ago

Running an LLM in fill-in-the-middle mode is like taking a few minutes to carefully build a fire, then stepping back and watching it burn.

TTS: Microsoft VibeVoice 1.5 B (community version)

Server: llama.cpp llama-server Models: IBM Granite 4.0 H Small 32 B Q6_K, IBM Granite 4.0 H Tiny 7 B Q6_K

Hardware: AMD Ryzen 7 6800H, 32 GB RAM, No GPU

llmpad: Written just for me by ChatGPT-5 in under an hour

Keywords
FREE email alerts of the most important BANNED videos in the world
Get FREE email alerts of the most important BANNED videos in the world that are usually blacklisted by YouTube, Facebook, Google, Twitter and Vimeo. Watch documentaries the techno-fascists don't want you to know even exist. Join the free Brighteon email newsletter. Unsubscribe at any time. 100% privacy protected.
Your privacy is protected. Subscription confirmation required.