Show HN: Fusion-runtime – self-hosted voice agents, STT+LLM+TTS in one process | Hacker News - But Better

Show HN: Fusion-runtime – self-hosted voice agents, STT+LLM+TTS in one process github.com

Self-hosted voice agent runtime: speech-to-text, an LLM and text-to-speech streaming into each other in one process. - SamarthUrs18/fusion-runtime

2 points•samarthurs18•9 days ago•1 comment•

#runtime #voice #self #hosted #process #fusion #llm #fusion runtime

1 comment

OrdersOfMagnitu9 days ago

How is the quality on longer runtimes? Does it degrade overtime? This would be a very useful addition if its entirely localized.

Read the full thread on Hacker News →

Related stories

"As a Language Model": Chat Template Switches LLM Self-Referential Voicearxiv.org
Hacker News · 89 points · 4 days ago
I built a self-improving voice AI agent that runs offline on a RPi5github.com
Hacker News · 2 points · 1 day ago
Mumble – Open-Source, Self-Hosted Voice Chatdigitalescapetools.com
Hacker News · 1 points · 10 days ago
Self-hosted, end-to-end encrypted 1:1 chat app. Offline key-exchangegithub.com
Hacker News · 1 points · 9 days ago
Self-hosted inference orchestrators compared: LocalAI, exo, GPUStack, vLLMnexlab.net
Hacker News · 10 points · 10 days ago
Show HN: A Self-hosted Deferred Deep linking. Firebase dynamic link modelgithub.com
Hacker News · 1 points · 9 days ago