DigitalHarvest

The FFmpeg and file-hash commands below run locally. No purchase is needed to follow them. In September 2026 we published a 140-second "music video" for one of our AI songs. It was one still picture with a small moving waveform along the bottom. Our pre-upload checks had measured the length, the resolution and the loudness. Nobody had checked whether the picture actually moved. We deleted it from our channel the next morning. This post shows the checks we run now. Every command below runs on your own computer with ffmpeg , and every number comes from files we measured ourselves. 1. Loudness and true peak (free, one command) ffmpeg -hide_banner -nostats -i song.mp4 -af ebur128=peak=true -f null - Read the Summary block at the end: I: is the integrated loudness in LUFS. Peak: under "True peak" is the true peak. ffmpeg prints the unit as dBFS. A test file we deliberately pushed too loud read I: -8.4 LUFS and Peak: 3.5 . Our own working baseline is ...

No affiliate links on this page (yet): nobody paid us for this guide and none of the links below earn us money. If we add affiliate links later, this box will be replaced by an advertising notice at the top of the page. What we did not do: we have not bought or tested any of the gear below. Every spec comes from the manufacturer's own page, linked next to it and checked on 28 September 2026. We do not quote prices because listings change by the hour. If you make music or short videos with AI tools, sooner or later you want to record something yourself: a vocal over an AI instrumental, a voice-over, an interview for a vlog. New gear is the simple option. Used, open-box and refurbished gear on eBay can cost less, but the labels are confusing and the protection depends on which label you pick. This page does two things. First, it explains in plain words what eBay's condition labels, refurbished warranty and Money Back Guarantee cover, quoting eBay's own pages. Secon...

An output_tp of −1.50 in an FFmpeg log does not mean your original audio has been fixed. A command can show that number without saving any corrected audio. Before uploading, measure the file you actually exported. This follow-up to our AI song quality checklist tackles one practical mistake: confusing filter output statistics with a saved deliverable. You need FFmpeg installed and a local audio file. These commands process files on your computer; they do not upload your recording. One recording, two different stages On September 18, 2026, we measured one newly generated, roughly 2-minute-20-second MP3. Its integrated loudness was −11.41 LUFS and its true peak was +0.84 dBTP . The same analysis log showed output_tp: -1.50 . input_i and input_tp describe the file supplied to that command. output_i and output_tp describe the signal after the filter in that execution. They do not establish the measured properties of a separately encoded final file. We then reduced gain by...

A correct caption does not prove an AI singer sang the correct words. A file that opens without errors can still have unclear lyrics, overloaded peaks or an awkward ending. Check those separately before choosing an export to upload. We reviewed three Gemini Lyria 3.5 song files made with new, AI-assisted Korean lyrics on September 14, 2026. Our evidence was local speech recognition, audio measurements and selected final-video frames. We did not complete a human listening review, and none of the three songs passed our publication check. These are workflow examples, not a benchmark of the music generator. What the three files actually showed Source MP3 measurements and main ASR results Check v1 v2 v3 Actual length 32.60s 61.96s 63.01s Exact lyric lines 2/6 2/6 2/6 Lines with any corresponding text 6/6 6/6 3/6 True peak, dBTP 0.0 +0.1 −0.1 “Exact” ignores spaces and punctuation. A focused v2 check recovered another line, but two key nouns stayed uncertain. Version three us...

Two videos can contain the same frames and still be different files. That matters when an upload folder contains original.mp4 , final.mp4 and another export that looks identical. We tested two specific cases with an owned sample instead of assuming the filenames told us what was inside. This is a companion to our short exact-copy demonstration. The original comparison below changes container metadata. The October 7 control adds a separate lossless and lossy re-encode; neither test represents every video editor or export setting. What we actually tested 1. Same contents, different name We copied the file and gave the copy a different name. Result: Same file. Its contents and size stayed the same. The new name did not make a new export. 2. Same decoded video, changed file We copied the video stream into a new MP4 container and changed its title metadata. Result: Different files. File contents changed. A separate comparison of the decoded video output matched for this sample. We...