Auto-captioning short clips locally with Whisper and FFmpeg: a practical guide
Short-form captions are not a decoration. On mute, they are the audio. A YouTube Short or TikTok clip...
Tag archive
Short-form captions are not a decoration. On mute, they are the audio. A YouTube Short or TikTok clip...

We build ClapClip, a Windows app that runs Whisper models locally, so read this with that in mind....

I sent my speech recognizer ten seconds of nothing and it heard "Thank you." Part 1 of how I learned to hear voice notes: real commands, real output,
Architecting a sovereign, self-hosted meeting intelligence stack using faster-whisper (CTranslate2 INT8) and Ollama with Nomily for zero-cloud audio transcription and summarization.
Cutting ums and long pauses out of a talking video is slow in a timeline editor. You find each one by...
Why the medium model is worth it for German, how to keep 9:16 lines around 16–18 characters when compounds run long, and how an initial_prompt plus a word list fixes names.
If you cut Shorts from podcasts or interviews, most of the clock time is not creative. It is the same...

At NobodyWho, we've spent the last months shipping new features, like Speech-to-Text or Voice...
A model-availability check should be a short-lived capability decision, not a prerequisite that makes...
TL;DR: Do not discover a speech model by sending it a customer recording. Keep a small capability...
I talk for 30 seconds, and my to-do list writes itself (Whisper + Gemma 4, local) ...
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle I built...