[{"data":1,"prerenderedAt":374},["ShallowReactive",2],{"project-17227564":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":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":43,"post_text":45,"what":46,"said":86,"maker_in_thread":189,"shape":200,"grid":204,"attempts":336,"same_week":337,"maker_shows":31,"maker_hidden":366,"reader_version":367,"card":368},"17227564","Podscripter","Automated Transcription for Podcasters","title","Show HN: Podscripter – Automated Transcription for Podcasters","https:\u002F\u002Fwww.podscripter.co\u002F?ref=hn","podscripter.co","craigcannon",1528119069,2018,153,59,263,2155,13,"notable","ai","speech to text transcription","web_app",[24,25,26,27],"podcast transcription","speech to text","speaker diarization","automated transcripts","curious",-0.076,{"positive":31,"neutral":32,"mixed":33,"critical":34},2,17,1,6,26,{"pricing":37,"docs":40,"idea":41,"execution":42},{"positive":38,"critical":39},0,3,{"positive":38,"critical":38},{"positive":31,"critical":31},{"positive":38,"critical":33},[38,33,39,38,39,39,33,39,39,38,44,38,39,39,39,39,39,38,39,39,38,39,33,38,39,38,39,38,38,33,38,44,33,39,38,38,39,38,38,33],5,null,{"problem":47,"audience":54,"pricing":58,"motivation":70,"time_to_build":45,"stack":74,"openness":84,"stage":85,"team_size":84},{"value":48,"source":49,"evidence":50},"Podcasters want transcripts without paying around $1 a minute for human transcription","maker",[51],{"id":52,"by":11,"text":53},"17227869","Hey HN! Craig from YC here. This project is a follow-up to SpeechBoard, which was a text-based audio editor - https:\u002F\u002Fnews.ycombinator.com\u002Fitem?id=15670827. Thanks for all the…",{"value":55,"source":49,"evidence":56},"Podcasters who want transcripts",[57],{"id":52,"by":11,"text":53},{"value":59,"source":60,"evidence":61},"About $10 per episode","commenter",[62,66],{"id":63,"by":64,"text":65},"17228429","jtbayly","For $10, I'd expect above 99% accuracy, especially since I can get an automated transcript for $5 for 60 minutes that presumably has a similar error rate to what you are…",{"id":67,"by":68,"text":69},"17229334","viridian","Hey Craig, I appreciate the hard work! Is there any way to demo this service for free, or any plans to in the future? The $10 isn't a big hit or anything, but I, as well as many…",{"value":71,"source":49,"evidence":72},"Creator had a podcast and could not justify paying $1 a minute for transcripts",[73],{"id":52,"by":11,"text":53},[75],{"value":76,"source":49,"evidence":77},"Google speech to text service",[78,81],{"id":79,"by":11,"text":80},"17229070","Google actually",{"id":82,"by":11,"text":83},"17230280","Google","unknown","launched",{"praise":87,"objections":103,"requests":117,"questions":141,"alternatives":156},[88],{"value":89,"source":60,"evidence":90},"Interest in automated transcripts with speaker separation for podcasts",[91,95,99],{"id":92,"by":93,"text":94},"17228548","raghavtoshniwal","Hey Craig, I wrote a service, (nowhere close for public release), that segments audio based on speakers. You have to identify one speech segment, it is then capable of labelling…",{"id":96,"by":97,"text":98},"17228663","joelrunyon","Would this integrate directly with zencastr? They record tracks individually - and then mix them - so you'd have direct access to the individual tracks. Seems like if you did…",{"id":100,"by":101,"text":102},"17229860","ocdtrekkie","I think this is super neat. The podcasts I am on do not make $10 an episode, so sadly, I can't justify it. But if I could, I would. I shared it with my podcasting friends.",[104,109,113],{"value":105,"source":60,"evidence":106},"Price is high for the accuracy and turnaround offered",[107,108],{"id":63,"by":64,"text":65},{"id":100,"by":101,"text":102},{"value":110,"source":60,"evidence":111},"24 hour turnaround is slower than cheap automated services",[112],{"id":63,"by":64,"text":65},{"value":114,"source":60,"evidence":115},"No free trial",[116],{"id":67,"by":68,"text":69},[118,124,131],{"value":119,"source":49,"evidence":120},"Free tier or demo",[121],{"id":122,"by":11,"text":123},"17230073","Yeah, we'll definitely have something free in the future. :) For the launch we wanted to make sure we could handle all the first orders quickly.",{"value":125,"source":60,"evidence":126},"Integration with Zencastr or uploaded unmixed tracks",[127,128],{"id":96,"by":97,"text":98},{"id":129,"by":11,"text":130},"17228876","Yeah, that's an awesome idea. I had kicked it around with some potential customers but went with this simpler model just to see if anyone was interested. Will most likely go for…",{"value":132,"source":60,"evidence":133},"Support for YouTube videos",[134,138],{"id":135,"by":136,"text":137},"17229500","lf275","Would you also do YouTube videos? There are many lectures online and it would be nice if more people transcribed them.",{"id":139,"by":11,"text":140},"17230467","Yeah, we could definitely do videos.",[142,149],{"value":143,"source":60,"evidence":144},"Can it transcribe phone calls?",[145],{"id":146,"by":147,"text":148},"17228751","mdocherty","Hello, Just curious if you are able to speech-to-text phone calls? Or if any point you plan to do so. Thanks",{"value":150,"source":60,"evidence":151},"Does it handle corrupted audio files?",[152],{"id":153,"by":154,"text":155},"17237337","roadrunner201","Can your service handle corrupted files? I record on the fly and I have some great interviews that I cannot play.",[157,168,175,182],{"value":158,"source":60,"evidence":159},"FluidDATA free automated transcripts",[160,164],{"id":161,"by":162,"text":163},"17228421","nibbleshift","FluidDATA has the Joe Rogan podcasts for free at https:\u002F\u002Ffluiddata.com\u002Fsearch?channel_id=9853 Not to mention, FluidDATA has transcribed over 8.2 million podcast episodes from…",{"id":165,"by":166,"text":167},"17228469","bmelton","Given the hand-curated speaking order, that seems hard. There are services out there that will do quality transcription that is completely automated (e.g., Bitplatter's…",{"value":169,"source":60,"evidence":170},"Trint and Temi",[171],{"id":172,"by":173,"text":174},"17230396","CharlesW","What distinguishes it from popular competitors like Trint, Temi, etc. who also do speaker identification?",{"value":176,"source":60,"evidence":177},"Scribie human transcription",[178],{"id":179,"by":180,"text":181},"17230653","braindead_in","Do try out https:\u002F\u002Fscribie.com\u002Ftranscription\u002Ffree as well once. Our diarisation system is around 90% accurate on longer paragraphs and will be out this week.",{"value":183,"source":60,"evidence":184},"Auphonic",[185],{"id":186,"by":187,"text":188},"17232103","jeena","For all practical reasons I'd say yes, I'm using https:\u002F\u002Fauphonic.com\u002F which does use machine learning to mute the parts where no human speaks, then they send this audio to third…",{"comments":190,"answered":191,"key":192},18,10,[193,194,197],{"id":52,"text":53},{"id":195,"text":196},"17228558","Thanks for the feedback. Ours are diarized accurately. I've yet to see an automated service that does that well.",{"id":198,"text":199},"17228822","Updated. Thanks for the feedback.",{"commenters":201,"max_depth":34,"maker_replies":190,"first_comment_mins":202,"lifespan_hours":203},29,37,24,[205,207,209,211,214,215,219,222,224,227,229,233,235,239,240,242,244,246,247,248,249,252,253,254,255,256,257,259,262,264,266,267,270,274,276,278,280,283,286,289,291,293,295,299,300,302,305,307,311,313,315,318,321,323,326,328,330,332,334],[52,38,38,206,11,33],"maker\u002Fneutral\u002Fidea",[63,38,33,208,64,38],"project\u002Fcritical\u002Fpricing",[195,38,38,210,11,33],"project\u002Fpositive\u002Fexecution",[212,38,39,213,64,38],"17228673","maker\u002Fneutral\u002Fdocs",[198,38,38,213,11,33],[216,38,39,217,218,38],"17228760","project\u002Fneutral\u002Fpricing","ghaff",[220,38,38,221,11,33],"17228914","commenter\u002Fneutral\u002Fnone",[223,38,39,217,218,38],"17229178",[225,38,33,208,226,38],"17229336","mindwork",[228,38,38,221,218,38],"17229455",[230,38,39,231,232,38],"17230442","project\u002Fneutral\u002Fidea","seanwilson",[234,38,38,231,11,33],"17232614",[236,38,39,237,238,38],"17229183","project\u002Fneutral\u002Fnone","knuththetruth",[82,38,38,237,11,33],[92,38,44,241,93,38],"project\u002Fpositive\u002Fidea",[243,38,38,241,11,33],"17228588",[179,38,38,245,180,38],"other\u002Fneutral\u002Fnone",[96,38,39,231,97,38],[129,38,38,241,11,33],[146,38,39,231,147,38],[250,38,39,237,251,38],"17229026","genieyclo",[79,38,38,237,11,33],[67,38,39,217,68,38],[122,38,38,217,11,33],[135,38,39,231,136,38],[139,38,38,231,11,33],[100,38,39,258,101,38],"project\u002Fmixed\u002Fpricing",[260,38,38,261,11,33],"17229941","maker\u002Fpositive\u002Fnone",[263,38,39,231,187,38],"17230216",[265,38,38,231,11,33],"17230271",[186,38,39,231,187,38],[268,38,39,231,269,38],"17231022","michaelmior",[271,38,33,272,273,38],"17232462","project\u002Fcritical\u002Fidea","asdsa5325",[275,38,38,221,269,38],"17233048",[277,38,38,221,273,38],"17233514",[153,38,39,279,154,38],"project\u002Fneutral\u002Fexecution",[281,33,38,245,282,38],"17229441","wenbin",[284,33,38,285,11,33],"17230326","other\u002Fpositive\u002Fnone",[287,31,39,231,288,38],"17228393","tomkinson",[161,31,38,290,162,38],"other\u002Fneutral\u002Fidea",[292,31,38,245,64,38],"17228702",[294,31,38,245,162,38],"17228941",[296,31,38,297,298,38],"17234974","other\u002Fcritical\u002Fnone","totoglazer",[165,31,33,208,166,38],[301,31,38,245,11,33],"17228681",[303,39,44,241,304,38],"17229446","pascalxus",[306,39,38,241,11,33],"17230478",[308,39,33,309,310,38],"17231196","project\u002Fcritical\u002Fexecution","rfreytag",[172,312,39,231,173,38],4,[314,312,38,231,11,33],"17232660",[316,44,38,290,317,38],"17230755","JasonFruit",[319,44,38,245,320,38],"17230771","bpicolo",[322,44,38,245,218,38],"17231042",[324,34,39,231,325,38],"17228380","superflyguy",[327,34,38,245,173,38],"17228487",[329,34,38,245,166,38],"17228505",[331,34,38,245,11,33],"17228605",[333,34,38,245,173,38],"17230208",[335,34,33,272,325,38],"17229270",[],[338,343,348,353,358,362],{"id":339,"name":340,"points":341,"category":342},"17226225","BitHubLab",318,"dev_tools",{"id":344,"name":345,"points":346,"category":347},"17242528","LogicEmu",210,"learning_science",{"id":349,"name":350,"points":351,"category":352},"17242136","Transity",190,"finance_crypto",{"id":354,"name":355,"points":356,"category":357},"17221221","Domain-tailored CRDTs for collaboration without server involvement",158,"languages",{"id":359,"name":360,"points":361,"category":347},"17246136","CircuitVerse",145,{"id":363,"name":364,"points":365,"category":342},"17236967","blush",127,false,"v2",{"id":369,"name":5,"line":6,"ai":366,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":370,"top":18,"kw":371,"maker":11,"domain":10,"tier":19,"attempts":38,"strip":372,"url":9,"mix":373,"praise":89,"objection":105,"sub":21},17227564,-0.08,[24,25,26,27],"0130331330503333303303103030010513003001",[31,32,33,34],1794036566607]