Project S.A.T.U.R.D.A.Y.
AI
voice assistant
SHOW HN2023
How HN took it
5 positive, 8 neutral or asking, 0 mixed, 4 critical, out of 17 comments about the project. Thread score +0.09.
Idea: 4 for, 1 againstPerformance: 0 for, 2 againstDocs: 1 for, 0 againstDesign: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Admired the maker's prior work and the open-source effort
From 1 comment
My skepticism at such overaching efforts is usually quite high. Apologies for discriminating on name/using popularity contest metrics, but seeing @grvydev's name on the repo…
rektide on HN
Idea of a self-hosted alternative to Alexa is appealing
From 2 comments
This is awesome! I've been waiting for LLMs to be combined with TTS like this, but my use case is somewhat silly: I like to take solo road trips, but I can only listen to so many…
roarcher on HNI love the idea. Is adding long term memory on the roadmap? How does it handle conversations now? Do you give the text to text engine the last 15 messages or something?
JCharante on HN
Objections
Response latency of several seconds is too slow for conversation
From 3 comments
Nice! I'm the creator of Willow[0] (which has been mentioned here). First of all, we love seeing efforts like this and we'd love to work together with other open source voice…
kkielhofner on HN> Yes, for my demo I am using whisper.cpp however there is an implementation that also uses faster-whisper. The benchmarks I referenced above show a GTX 1070 beating an…
kkielhofner on HNSomewhat covered by other comments, but what I would want to see to evaluate a project like this is your current response latency and your goal latency for each step, or ideas…
cjbprime on HN
Vocal computing is not the long-term future; thought interfaces may replace it
From 1 comment
"In my mind vocal computing is the future of human-computer interaction" ...really though? That's the future? Not telepathic unspoken 1:1 mindmelding? Who wants to flap their…
Solvency on HN
Always-on microphones and cameras raise privacy concerns
From 1 comment
Given how easily 24-hour access to mics and cameras can be abus… commercialized, I think I'd rather waste my breath.
cwillu on HN
Requests
Add long-term conversation memory
From 1 comment
I love the idea. Is adding long term memory on the roadmap? How does it handle conversations now? Do you give the text to text engine the last 15 messages or something?
JCharante on HN
Add hotword detection instead of mute/unmute
From 1 comment
looks super cool, i was planning to do the same thing! are you planning to add hotword detection - instead of mute/unmute? I saw this https://picovoice.ai/platform/porcupine/ but…
nerdyboi on HN
Report response latency figures
From 1 comment
Somewhat covered by other comments, but what I would want to see to evaluate a project like this is your current response latency and your goal latency for each step, or ideas…
cjbprime on HN
Questions
How does the system handle conversation history?
From 1 comment
I love the idea. Is adding long term memory on the roadmap? How does it handle conversations now? Do you give the text to text engine the last 15 messages or something?
JCharante on HN
Is there a video demo?
From 1 comment
Just wondering if there is a video or demo, or anything so we can see it before going through and trying it out? It seems super cool
catchmeifyoucan on HN
Alternatives named
Willow voice assistant
From 2 comments
Maybe tie in the ESP BOX as an open-ish Alexa like Willow. https://news.ycombinator.com/item?id=35948462
password4321 on HNNice! I'm the creator of Willow[0] (which has been mentioned here). First of all, we love seeing efforts like this and we'd love to work together with other open source voice…
kkielhofner on HN
Rasa NLU
From 1 comment
Nice! I'm the creator of Willow[0] (which has been mentioned here). First of all, we love seeing efforts like this and we'd love to work together with other open source voice…
kkielhofner on HN
Picovoice Porcupine
From 1 comment
looks super cool, i was planning to do the same thing! are you planning to add hotword detection - instead of mute/unmute? I saw this https://picovoice.ai/platform/porcupine/ but…
nerdyboi on HN