Posts

FFmpeg Shows −1.5 dBTP. Did You Actually Fix the Audio?

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...
Post a Comment
Read more

US Travel eSIM: Only 12 of Airalo's 30 US Plans Include Calls and Texts

Disclosure: we earn a commission if you book through the affiliate store links on our checklist page linked below. The "United States eSIM" button below goes to that checklist page; the store links there are affiliate links. This post was drafted with AI assistance and checked line by line against Airalo's public pages; Airalo did not provide or review it. Go straight to the store link: United States eSIM button on our checklist page . That button opens Airalo's US country page, not a preselected plan, so you still choose the plan and see the final total there. Observed on 30 October 2026, 12:10 KST from Airalo's public United States eSIM page and two of its help articles. Listings change; read the plan details again before you pay. Most of the 30 US listings are data only The United States page listed 30 plans at the time of this observation. They fall into three groups: 12 fixed-data plans (operator name "Change") from 1 GB for 3 days up to 5...
Post a Comment
Read more

Loudness Check on 15 AI Shorts: 3 Missed -14 LUFS, and loudnorm Didn't Always Land

Disclosure: this post has no affiliate links. The shop page linked at the end is our own product list and may contain affiliate links; we may earn a commission if you buy through those. All 15 videos measured here are short videos we made ourselves with AI tools, and this post was drafted with AI assistance, then checked against our measurement file from October 30, 2026 (KST). No tool vendor provided or reviewed it. Short answer from one batch: we measured the audio of 15 finished vertical shorts from our own production folders against a target of -14 LUFS integrated loudness and a -1 dBTP true-peak ceiling. 12 of the 15 were already within 1 LU of the target. The three that were not had been quieter: -17.9, -16.1 and -39.3 LUFS. When we ran FFmpeg's loudnorm filter on all 15, the one-pass version missed the target by up to 3.4 LU, and even the measured two-pass version missed by up to 1.5 LU on four files. Every one of those four two-pass misses was a file where loudnorm report...
Post a Comment
Read more

CRF 18 vs 23 vs 28 for a Vertical AI Short: File Size and VMAF on One 10-Second Clip

Disclosure: this post has no affiliate links. The shop page linked at the end is our own product list and may contain affiliate links; we may earn a commission if you buy through those. The test clip is an AI-generated video we made ourselves, and this post was drafted with AI assistance, then checked line by line against our measurement file from October 29, 2026 (KST). No tool vendor provided or reviewed it. Short answer from one test: on our 10-second vertical AI clip, each 5-step rise in CRF cut the file by 41-51% (about half from CRF 23 upward), and CRF 23 on the x264 "veryfast" preset was not the same quality as CRF 23 on "medium". Veryfast made a file 30% smaller, but its VMAF score (91.93) landed next to medium at CRF 28 (92.18), not next to medium at CRF 23 (95.97). If you change the preset to save time, do not assume the CRF number still means the same quality. The question You export a 1080×1920 short and have to pick a CRF value. Lower CRF means a b...
Post a Comment
Read more

Whisper Tiny vs Turbo for AI Voiceover Captions: Tiny Wrote "Paths" for "Pass"

Disclosure: this post has no affiliate links. The shop page linked at the end is our own product list and may contain affiliate links; we may earn a commission if you buy through those. This is our own test log from October 28, 2026 (KST). No tool vendor provided or reviewed it. Short answer from one small test: for English captions of a clean AI voiceover, the smallest Whisper model was not enough, but the second smallest nearly was. We ran four local Whisper sizes (tiny, base, small, large-v3-turbo) three times each on two 21–22-second takes of the same 73-word narration. Small and large-v3-turbo matched the script word for word on both takes. Base matched one take and split "voiceover" into "voice over" on the other. Tiny made the same 3 word errors on both takes, and one of them changed the meaning: "If all three pass" became "If all three paths". Speed did not decide anything here: every model finished each clip in under 6 seconds on our l...
Post a Comment
Read more

Japan eSIM: why the 7-day unlimited plan costs more per day than the 5-day

This post contains affiliate links; we earn a commission if you book through them. Prices as of 27 October 2026, 10:01 KST , read from Airalo's public Japan eSIM page in USD. Prices may change; check the current price on the booking page before you pay. Why does the 7 -day unlimited plan cost more per day than the 5 -day one? Longer plans are usually cheaper per day. On Airalo's Japan unlimited list that was not true at every step in this observation. Unlimited plan Price Per day 3 days $11.50 $3.83 5 days $17.00 $3.40 7 days $26.50 $3.79 10 days $34.50 $3.45 15 days $48.00 $3.20 30 days $69.00 $2.30 Unlimited fair-use condition: Lower speed rate of 1 Mbps after 3 GB usage per day. This condition was listed for every unlimited plan above; unlimited does not mean unlimited full-speed data. 7 days at $26.50 works out to about $3.79 a day, more than 5 days at $17.00 (about $3.40 a day). Two 5 -day plans add up to $34.00 , compared with $34.50 for one 10 -day p...
Post a Comment
Read more

Local AI Voice on a Laptop CPU: 73 Words Took About 2.5 Minutes per Take

No affiliate links in this post. This is our own production log from October 27, 2026 (KST). No tool vendor provided or reviewed it. The voice clips were made with a local AI model (an AI voice cloned from a reference clip that the same model generated from a text description, not a real person's voice) and were not published. Short answer from one small test: on a laptop CPU with no GPU, the free local model VoxCPM2 voiced a 73-word narration in about two and a half minutes per take. It produced 21–22 seconds of speech, and Whisper transcribed every word correctly in both takes. That is roughly 6–7 seconds of waiting for every second of audio. If you voice one short script at a time and can wait, local is enough for that job. The model card's speed figure was measured on an RTX 4090 GPU and does not carry over to a CPU. The question You want a voiceover of about half a minute for a short video and you are not paying for a hosted voice service. Can a free local model do it...
Post a Comment
Read more

How to Fit an AI Voiceover to an Exact Length Without Changing Pitch

No affiliate links in this post. This is our own production log from October 26, 2026 (KST). No tool vendor provided or reviewed it, and we did not test ElevenLabs or any other hosted voice service here. The voice clips were made with a local AI model and were not published. Short answer from one small test: if your AI voiceover runs a little long, FFmpeg's atempo filter sped our VoxCPM2 clips up by about 11–13% to fit a 5.5-second slot, with almost no change in pitch, and Whisper still transcribed every word. It landed 8–19 milliseconds short of the target, and adding apad padded the files out to exactly 5.50 seconds. Simply resampling the audio (the "sped-up tape" method) also hit 5.50 seconds, but it raised the voice by roughly 10–12% on our rough pitch estimate. The question You have a 5.5-second slot in an edit and the narration comes out at 6.2 seconds. Hosted voice services often have a speed control. ElevenLabs documents a Speed setting from 0.7 to 1.2, def...
Post a Comment
Read more