Who it is forSomeone with an interview or meeting recording and no transcript.
The problemPlain Whisper timestamps drift and manual syncing is slow.
The outcomeA transcript with accurate word-level timing.
What you need first
- Python with pip, ffmpeg may also be needed
- A GPU with CUDA toolkit 12.8 for speed, CPU also works
- A Hugging Face read token for speaker diarization
Steps
- Install WhisperX with
pip install whisperx - Run
whisperx path/to/audio.wavto transcribe with default settings - Add
--highlight_words Trueto see word timings in the .srt file - Open the output files and check the timing against the audio
Prompt for your agent
Using m-bain/whisperX, install it with `pip install whisperx`, run `whisperx <my audio file> --highlight_words True`, then summarize what output files were created.
Caveat. Words like 2014. or 13.60 pounds that lack alignment characters get no timing.
Use this in your AI agent
Ask your agent
Using the Deduped MCP, get the setup steps for m-bain/whisperX and "Transcribe an audio file with word timings"
Add Deduped to Claude Code once
claude mcp add --transport http deduped https://dedupedai.com/mcp
Every Monday: the 5 hottest repos and exactly how to use them. Free, one email a week, unsubscribe anytime.
Get them freeShare: X LinkedIn Hacker News Email Copy link
Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer