[{"data":1,"prerenderedAt":247},["ShallowReactive",2],{"guide-en-turn-a-meeting-recording-into-notes":3,"guide-en-turn-a-meeting-recording-into-notes-related":236},{"id":4,"title":5,"author":6,"body":7,"date":221,"description":222,"difficulty":223,"extension":224,"image":225,"lastModified":221,"meta":226,"navigation":227,"outcome":228,"path":229,"readingTime":230,"robots":225,"scenario":231,"seo":232,"stem":233,"tools":234,"__hash__":235},"guides\u002F8.guides\u002F2.turn-a-meeting-recording-into-notes.md","How to Turn a Meeting into Searchable Text","FlowPick Team",{"type":8,"value":9,"toc":210},"minimark",[10,14,19,22,25,28,32,41,48,54,57,63,68,71,75,78,86,89,95,100,104,112,115,122,128,134,139,142,146,149,155,160,163,167,173,179,185,191,195,198],[11,12,13],"p",{},"Ten minutes after a meeting ends, nobody remembers what was decided. The recording exists, but scrubbing a 70-minute video to find one number is worse than having no recording. This guide turns the file into something searchable.",[15,16,18],"h2",{"id":17},"what-this-workflow-does-and-does-not-do","What this workflow does and does not do",[11,20,21],{},"It produces a transcript: timestamped text, editable, exportable as TXT, SRT or VTT. That is the raw material for minutes.",[11,23,24],{},"It does not summarise. There is no \"summarise this meeting\" button, and the transcription tools do not translate or identify speakers. If you need a summary, you write it from the transcript — which is usually faster than writing it from the video, because you can skim.",[11,26,27],{},"One constraint worth knowing before you start: recognition runs on your own machine, so duration is cost. In our runs, a 70-minute meeting on a laptop CPU took long enough that trimming was not optional.",[15,29,31],{"id":30},"step-1-trim-before-you-transcribe","Step 1: Trim before you transcribe",[11,33,34,35,40],{},"Open the recording in the ",[36,37,39],"a",{"href":38},"\u002Ftools\u002Fvideo-trimmer","video trimmer"," and cut two things: the stretch at the front where people join and check their audio, and the tail after the last decision.",[11,42,43],{},[44,45],"img",{"alt":46,"src":47},"A 70-minute recording split into 9 minutes of joining, 45 minutes of agenda and 15 minutes of closing chat; only the agenda is kept","\u002Fimg\u002Fguides\u002Ftrim-before-transcribe.svg",[11,49,50],{},[51,52,53],"em",{},"Recognition cost scales with duration. Cutting the first nine minutes removes 13% of the work before it starts.",[11,55,56],{},"This is the highest-leverage step, and the reason is arithmetic rather than tidiness: a meeting that starts nine minutes late becomes 13% shorter after the cut, and the parts you removed contain nothing you need.",[11,58,59],{},[44,60],{"alt":61,"src":62},"Video trimmer with a selection from one to three seconds and a two-second output duration","\u002Fimg\u002Fguides\u002Fvideo-trimmer-timeline.jpg",[11,64,65],{},[51,66,67],{},"Interface example using the four-second FlowPick test video. The highlighted range keeps 0:01–0:03; apply the same controls to your meeting.",[11,69,70],{},"Keep the original. Trimming produces a new file, and you will want to go back to the untouched version if a decision turns out to be ambiguous.",[15,72,74],{"id":73},"step-2-convert-webm-to-mp4-only-if-transcription-fails","Step 2: Convert WebM to MP4 only if transcription fails",[11,76,77],{},"Browser screen recorders, and several meeting clients, write WebM with Opus audio. That is a perfectly good format, and the transcriber often handles it — but \"often\" is doing real work in that sentence, because container and audio decoding support differ between Chrome, Edge and Firefox, and the audio track is what matters here, not the picture.",[11,79,80,81,85],{},"If the transcriber reports that it cannot decode the audio, or silently finds no speech, convert first with the ",[36,82,84],{"href":83},"\u002Ftools\u002Fwebm-to-mp4","WebM to MP4 converter"," and try the MP4.",[11,87,88],{},"Skip this step if transcription already works. Converting a file that was going to be fine costs a few minutes for nothing.",[11,90,91],{},[44,92],{"alt":93,"src":94},"WebM conversion result showing an 88.9 KB VP8 Opus source and a 122.3 KB MP4 output","\u002Fimg\u002Fguides\u002Fwebm-to-mp4-result.jpg",[11,96,97],{},[51,98,99],{},"Generated four-second test video: 88.9 KB WebM → 122.3 KB MP4. This tool re-encodes to H.264\u002FAAC; output size depends on the source and settings.",[15,101,103],{"id":102},"step-3-transcribe-choosing-the-model-deliberately","Step 3: Transcribe, choosing the model deliberately",[11,105,106,107,111],{},"Open ",[36,108,110],{"href":109},"\u002Ftools\u002Fvideo-to-text","Video to Text",", select the trimmed MP4, set the spoken language, and start.",[11,113,114],{},"Two settings decide how long this takes:",[11,116,117,121],{},[118,119,120],"strong",{},"Model size."," The lightweight model downloads 40–150 MB of weights and is the right choice for a meeting where you only need to find decisions. The standard model downloads 80–250 MB and recognises more, especially names and technical terms, at the cost of time and memory.",[11,123,124,127],{},[118,125,126],{},"Processing mode."," GPU acceleration helps if the browser exposes it. Auto mode falls back to CPU when it cannot confirm a usable GPU, which is common on laptops with integrated graphics.",[11,129,130],{},[44,131],{"alt":132,"src":133},"Video transcription settings with spoken language, Whisper Tiny and Base model choices, and CPU processing","\u002Fimg\u002Fguides\u002Fvideo-to-text-settings.jpg",[11,135,136],{},[51,137,138],{},"Transcription settings for the generated English speech sample. Model choice and processing mode affect download size and processing time.",[11,140,141],{},"Language is the setting people get wrong most often. Auto-detection reads the first stretch with speech and applies that for the rest; a meeting that opens with two people chatting in another language will be misdetected. If you know the language, set it.",[15,143,145],{"id":144},"step-4-correct-the-parts-that-matter","Step 4: Correct the parts that matter",[11,147,148],{},"Click a timestamp to play the video from that point, then fix the text. You do not need to correct everything. Names, numbers, dates and action items are worth the effort; filler is not.",[11,150,151],{},[44,152],{"alt":153,"src":154},"Video transcript with an editable segment, a zero-to-five-second timestamp and TXT SRT VTT export buttons","\u002Fimg\u002Fguides\u002Ftranscript-editing.jpg",[11,156,157],{},[51,158,159],{},"Actual Whisper Tiny CPU output from the generated speech sample, before correction. It misheard “two short sentences” as “new short sentences”; review the audio before quoting.",[11,161,162],{},"Timestamps are approximate. If the transcript is going to become subtitles, plan on adjusting the timing in your editor rather than trusting it exactly.",[15,164,166],{"id":165},"where-this-goes-wrong","Where this goes wrong",[11,168,169,172],{},[118,170,171],{},"Music at the start confuses detection."," Overlapping speakers and background music both hurt recognition. Trimming the intro in step 1 solves most of it.",[11,174,175,178],{},[118,176,177],{},"The transcript is a wall of text with no line breaks."," The output is segmented by recognition windows, not by speaker or sentence. Expect to restructure it when writing minutes.",[11,180,181,184],{},[118,182,183],{},"A long recording stops partway."," Completed sections are kept. You can export what exists, or split the source file and transcribe the halves separately — which is also the workaround for a browser that runs out of memory.",[11,186,187,190],{},[118,188,189],{},"Someone spoke in a language the model handles poorly."," This version supports the languages listed in the tool, and quality varies by language. Check the output before quoting anything.",[15,192,194],{"id":193},"what-you-end-up-with","What you end up with",[11,196,197],{},"Three files from one session: the trimmed MP4 for anyone who wants to watch, an editable transcript for grepping, and an SRT if you need captions.",[11,199,200,201,205,206,209],{},"For the subtitle-specific path — burning them in, checking timing on a timeline — see ",[36,202,204],{"href":203},"\u002Fdocs\u002Ffeatures\u002Fformat-conversion","format conversion"," and the ",[36,207,208],{"href":109},"SRT export notes",".",{"title":211,"searchDepth":212,"depth":212,"links":213},"",2,[214,215,216,217,218,219,220],{"id":17,"depth":212,"text":18},{"id":30,"depth":212,"text":31},{"id":73,"depth":212,"text":74},{"id":102,"depth":212,"text":103},{"id":144,"depth":212,"text":145},{"id":165,"depth":212,"text":166},{"id":193,"depth":212,"text":194},"2026-10-29","Screen recordings arrive as WebM with the waiting at the front. Trim first, convert only if the audio will not decode, then transcribe. Includes what recognition does badly and how long it takes.","basic","md",null,{},true,"A trimmed MP4 for sharing, plus an editable transcript and SRT file from the same run.","\u002Fguides\u002Fturn-a-meeting-recording-into-notes",7,"transcribe",{"title":5,"description":222},"8.guides\u002F2.turn-a-meeting-recording-into-notes",[38,83,109],"WCxWAx5vHs1M4oB2YcAUKKdWrdKdLbkTlRtGxgzeTfQ",[237,239],{"path":229,"title":5,"description":222,"tools":238},[38,83,109],{"path":240,"title":241,"description":242,"tools":243},"\u002Fguides\u002Fpull-one-answer-from-a-podcast","How to Pull One Answer Out of a Two-Hour Podcast","You do not need to transcribe two hours to find eight minutes. Locate the passage in the audio, cut it, then transcribe the cut. A guide to the shortest path from a podcast URL to a quotable transcript.",[244,245,246],"\u002Faudio-downloader","\u002Ftools\u002Faudio-trimmer","\u002Ftools\u002Faudio-to-text",1793546743826]