"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.
Troed Sångberg
npub192…vy8wk
2026-07-28 10:17:53 UTC
Author Public Key
npub192kepsf3ypyzgsds9r93amadzta0efs05ftuxhl84m04e9xxhy9qevy8wkPublished at
2026-07-28 10:17:53 UTCEvent JSON
{
"id": "6113a71065b729c5a82b53515c0ff639ee5ace40240e43c4fdbac546347eff99",
"pubkey": "2aad90c13120482441b028cb1eefad12fafca60fa257c35fe7aedf5c94c6b90a",
"created_at": 1785233873,
"kind": 1,
"tags": [
[
"proxy",
"https://swecyb.com/@troed/116997087134611615",
"web"
],
[
"proxy",
"https://swecyb.com/users/troed/statuses/116997087134611615",
"activitypub"
],
[
"L",
"pink.momostr"
],
[
"l",
"pink.momostr.activitypub:https://swecyb.com/users/troed/statuses/116997087134611615",
"pink.momostr"
],
[
"-"
]
],
"content": "\"speech-to-speech\" is a project by Huggingface - an easily deployable local VAD-STT-LLM-TTS pipeline.\n\nI 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.\n\nThe 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.\n\nThis 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.",
"sig": "ba505893f57cd8df9d274d2c587863b234f1679ec617aabaad51b4684858b566003bf628954fc073492dfa541c3b54e24a0cef5304c61427f010260ff6725291"
}