Audio to text, on your terms

Transcribe any file to text and SRT. Privately.

Drop in an mp3, m4a, wav, mp4, ogg or flac. WhisperClip sends it straight to the transcription API you configure with your own key, and writes clean text plus a timestamped SRT. There is no WhisperClip server: your files never touch us.

$ node src/transcribe.mjs interview.mp3 --srt
Saved text to interview.txt · Saved SRT to interview.srt

€14.99 one-time · lifetime license

You'll get a license key + download link after payment. Requires your own Groq API key (free tier works). No experience needed. A plain-English, click-by-click setup guide is included: read it now.

Prerequisites (read before buying)

Node.js 18+ — no other dependencies to install (zero npm deps). New to this? The zip includes a one-click installer (setup.bat for Windows, install.sh for Mac/Linux) and a full beginner guide.
Your own Groq API key (free tier at console.groq.com — 2-minute signup, step-by-step in the guide). WhisperClip sends audio straight to Groq with your key; there is no WhisperClip server.
You pay Groq directly for transcription API usage — the tool itself is a one-time purchase.
Try before you buy: demo mode transcribes the first ~30 seconds of any file, free.

What you get

Plain-text transcript plus SRT with timestamps — ready for captions or notes.
Zero dependencies: it's a single Node script, nothing to bundle.
BYO key, so you control cost and where your data goes.
Demo mode works out of the box — try before you buy; a license unlocks unlimited use.

FAQ

Do I need a paid key?: No — Groq's free tier covers real usage, and any OpenAI-compatible endpoint works.
Is my audio uploaded anywhere by this tool?: No. It goes only to the provider you point it at, with your key. There is no middleman server.
Languages?: Anything the underlying whisper model supports; pass --lang to hint.