Post #4160781
2026-07-28 10:17 UTC
"speech-to-speech" is a project by Huggingface - an easily deployable local VAD-STT-LLM-TTS pipeline.
I now have Majel Barrett (the voice of the computer in ST:TNG) answering my questions about the upcoming family vacation in Croatia. This is the stuff of dreams from the 90s having come real.
The VAD/TTS/STT components run on one computer and the LLM on another - everything GPU accelerated. The response time is even shorter than the one in TNG.
This household have no listening microphones or indoor cameras for privacy reasons, but a completely local setup on a separate VLAN ... hmm. I need to think about this.
Replies (2)
-
@troed@swecyb.com 2026-07-28 18:51
My Star Trek-ified fork of the repo can be found here. It's quite close to behaving and sounding exactly like TNG, but you'll have to supply the right voice clone and chimes audio yourself ;) https://github.com/troed/speech-to-speech
-
@Professor_Stevens@mastodon.gamedev.place 2026-07-28 10:52
@troed@swecyb.com This is my world: Majel Barrett is now "The voice of the computer in ST:TNG." The woman who created the character who made unrequited love for Spock a thing, and who was the first to play a Trek second-in-command, is now "the voice of the computer in ST:TNG." A piece of my life just died.