[{"data":1,"prerenderedAt":310},["ShallowReactive",2],{"project-36564923":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":27,"sentiment":28,"stance_mix":29,"scored_comments":18,"aspects":34,"strip":41,"post_text":43,"what":44,"said":79,"maker_in_thread":174,"shape":186,"grid":190,"attempts":272,"same_week":273,"maker_shows":33,"maker_hidden":302,"reader_version":303,"card":304},"36564923","Project S.A.T.U.R.D.A.Y.","open-source, self hosted, J.A.R.V.I.S.","title","Show HN: Project S.A.T.U.R.D.A.Y. – open-source, self hosted, J.A.R.V.I.S.","https:\u002F\u002Fgithub.com\u002FGRVYDEV\u002FS.A.T.U.R.D.A.Y","github.com","GRVYDEV",1688326965,2023,121,30,527,3109,17,"notable","ai","voice assistant","library",[21,24,25,26],"whisper.cpp","self-hosted","text to speech","mixed",0.088,{"positive":30,"neutral":31,"mixed":32,"critical":33},5,8,0,4,{"docs":35,"idea":37,"performance":38,"design":40},{"positive":36,"critical":32},1,{"positive":33,"critical":36},{"positive":32,"critical":39},2,{"positive":32,"critical":36},[42,32,30,32,36,32,32,32,32,32,32,42,30,32,30,30,32,42,32,42,42,36,36,32,36,42,42,32,42,32,30],3,"Welcome to Project S.A.T.U.R.D.A.Y. This is a project that allows anyone to easily build their own self-hosted J.A.R.V.I.S-like voice assistant. In my mind vocal computing is the future of human-computer interaction and by open sourcing this code I hope to expedite us on that path.\n\nI have had a blast working on this so far and I'm excited to continue to build with it. It uses whisper.cpp [1], Coqui TTS [2] and OpenAI [3] to do speech-to-text, text-to-text and text-to-speech inference all 100% locally (except for text-to-text). In the future I plan to swap out OpenAI for llama.cpp [4]. It is b",{"problem":45,"audience":51,"pricing":55,"motivation":56,"time_to_build":55,"stack":60,"openness":76,"stage":77,"team_size":78},{"value":46,"source":47,"evidence":48},"Building a self-hosted voice assistant with speech-to-text, text-to-text and text-to-speech","maker",[49],{"id":50},"post",{"value":52,"source":47,"evidence":53},"Developers wanting to build vocal computing applications",[54],{"id":50},null,{"value":57,"source":47,"evidence":58},"Expedite vocal computing as the future of human-computer interaction",[59],{"id":50},[61,64,68,72],{"value":24,"source":47,"evidence":62},[63],{"id":50},{"value":65,"source":47,"evidence":66},"Coqui TTS",[67],{"id":50},{"value":69,"source":47,"evidence":70},"OpenAI",[71],{"id":50},{"value":73,"source":47,"evidence":74},"WebRTC",[75],{"id":50},"open_source","beta","unknown",{"praise":80,"objections":100,"requests":129,"questions":145,"alternatives":157},[81,89],{"value":82,"source":83,"evidence":84},"Admired the maker's prior work and the open-source effort","commenter",[85],{"id":86,"by":87,"text":88},"36567109","rektide","My skepticism at such overaching efforts is usually quite high. Apologies for discriminating on name\u002Fusing popularity contest metrics, but seeing @grvydev's name on the repo…",{"value":90,"source":83,"evidence":91},"Idea of a self-hosted alternative to Alexa is appealing",[92,96],{"id":93,"by":94,"text":95},"36578325","roarcher","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…",{"id":97,"by":98,"text":99},"36568669","JCharante","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?",[101,115,122],{"value":102,"source":83,"evidence":103},"Response latency of several seconds is too slow for conversation",[104,108,111],{"id":105,"by":106,"text":107},"36572244","kkielhofner","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…",{"id":109,"by":106,"text":110},"36577580","> 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…",{"id":112,"by":113,"text":114},"36601308","cjbprime","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…",{"value":116,"source":83,"evidence":117},"Vocal computing is not the long-term future; thought interfaces may replace it",[118],{"id":119,"by":120,"text":121},"36569240","Solvency","\"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…",{"value":123,"source":83,"evidence":124},"Always-on microphones and cameras raise privacy concerns",[125],{"id":126,"by":127,"text":128},"36569568","cwillu","Given how easily 24-hour access to mics and cameras can be abus… commercialized, I think I'd rather waste my breath.",[130,134,141],{"value":131,"source":83,"evidence":132},"Add long-term conversation memory",[133],{"id":97,"by":98,"text":99},{"value":135,"source":83,"evidence":136},"Add hotword detection instead of mute\u002Funmute",[137],{"id":138,"by":139,"text":140},"36576170","nerdyboi","looks super cool, i was planning to do the same thing! are you planning to add hotword detection - instead of mute\u002Funmute? I saw this https:\u002F\u002Fpicovoice.ai\u002Fplatform\u002Fporcupine\u002F but…",{"value":142,"source":83,"evidence":143},"Report response latency figures",[144],{"id":112,"by":113,"text":114},[146,150],{"value":147,"source":83,"evidence":148},"How does the system handle conversation history?",[149],{"id":97,"by":98,"text":99},{"value":151,"source":83,"evidence":152},"Is there a video demo?",[153],{"id":154,"by":155,"text":156},"36565290","catchmeifyoucan","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",[158,166,170],{"value":159,"source":83,"evidence":160},"Willow voice assistant",[161,165],{"id":162,"by":163,"text":164},"36567729","password4321","Maybe tie in the ESP BOX as an open-ish Alexa like Willow. https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=35948462",{"id":105,"by":106,"text":107},{"value":167,"source":83,"evidence":168},"Rasa NLU",[169],{"id":105,"by":106,"text":107},{"value":171,"source":83,"evidence":172},"Picovoice Porcupine",[173],{"id":138,"by":139,"text":140},{"comments":31,"answered":175,"key":176},7,[177,180,183],{"id":178,"text":179},"36569300","Thank you for the very kind words :)",{"id":181,"text":182},"36569291","If you really think about it every future is near term with a shelf life :)",{"id":184,"text":185},"36569299","Yeah adding memory is absolutely on the road map! For now everything is quite simple to allow for us to build over time but I plan to put a lot of work into the text to text…",{"commenters":187,"max_depth":33,"maker_replies":31,"first_comment_mins":188,"lifespan_hours":189},22,42,67,[191,195,199,201,203,205,206,208,212,215,218,221,223,225,226,227,229,232,233,236,238,240,245,248,251,252,255,260,262,266,268],[192,32,42,193,194,32],"36567705","project\u002Fneutral\u002Fdocs","ChrisArchitect",[196,32,32,197,198,32],"36569729","commenter\u002Fneutral\u002Fnone","adhesive_wombat",[86,36,30,200,87,32],"maker\u002Fpositive\u002Fidea",[178,36,32,202,11,36],"commenter\u002Fpositive\u002Fnone",[119,39,36,204,120,32],"project\u002Fcritical\u002Fidea",[181,39,32,197,11,36],[126,39,32,207,127,32],"other\u002Fcritical\u002Fprivacy",[209,39,32,210,211,32],"36571071","other\u002Fneutral\u002Fnone","blitzar",[213,39,32,210,214,32],"36591583","Takennickname",[216,39,32,197,217,32],"36571223","dabluecaboose",[219,39,32,197,220,32],"36571311","dtx1",[162,42,42,222,163,32],"project\u002Fneutral\u002Fidea",[97,33,30,224,98,32],"project\u002Fpositive\u002Fidea",[184,33,32,222,11,36],[93,30,30,224,94,32],[138,228,30,224,139,32],6,[230,228,32,231,11,36],"36576805","maker\u002Fneutral\u002Fidea",[154,175,42,193,155,32],[234,175,32,235,11,36],"36565337","maker\u002Fneutral\u002Fdocs",[112,31,42,237,113,32],"project\u002Fneutral\u002Fperformance",[239,31,42,237,113,32],"36601514",[241,242,36,243,244,32],"36567631",9,"project\u002Fcritical\u002Fdesign","ilaksh",[105,246,36,247,106,32],10,"project\u002Fcritical\u002Fperformance",[249,246,32,250,11,36],"36576782","maker\u002Fmixed\u002Fperformance",[109,246,36,247,106,32],[253,246,42,237,254,32],"36589548","jzombie",[256,257,42,258,259,32],"36569050",11,"maker\u002Fneutral\u002Fdesign","thatxliner",[261,257,32,258,11,36],"36569304",[263,264,42,193,265,32],"36569277",12,"DANmode",[267,264,32,235,11,36],"36569307",[269,264,30,270,271,32],"36570603","maker\u002Fpositive\u002Fdocs","dang",[],[274,279,284,289,294,298],{"id":275,"name":276,"points":277,"category":278},"36605493","Hacker News user blogroll",937,"consumer_social",{"id":280,"name":281,"points":282,"category":283},"36582468","Degrees What",171,"dev_tools",{"id":285,"name":286,"points":287,"category":288},"36591767","varun.ca",159,"creative",{"id":290,"name":291,"points":292,"category":293},"36590834","FerretDB",147,"data",{"id":295,"name":296,"points":297,"category":20},"36520410","Windmill knowledge base Discord bot",144,{"id":299,"name":300,"points":301,"category":283},"36543398","Tabserve.dev",117,false,"v2",{"id":305,"name":5,"line":6,"ai":302,"cat":20,"year":13,"points":14,"comments":15,"rec":27,"s":306,"top":18,"kw":307,"maker":11,"domain":10,"tier":19,"attempts":32,"strip":308,"url":9,"mix":309,"praise":82,"objection":102,"sub":21},36564923,0.09,[21,24,25,26],"3050100000035055030331101330305",[30,31,32,33],1794036637816]