Murmurhouse · Guide

Turn audio into text for free, without uploading it

Most “free” transcription sites upload your recording to their servers and limit how many minutes you get. Murmurhouse runs the speech model in your own browser instead, so there’s nothing to upload and nothing to count.

How to do it

1. Open Murmurhouse in Chrome, Edge, Firefox or Safari.
2. Drop your file (MP3, M4A, WAV, OGG, FLAC…) or press Record to use your microphone.
3. Pick the language, or leave it on automatic. Choose Fast for quick drafts or Balanced for better accuracy.
4. Wait while your computer transcribes. The first time, it downloads the speech model once.
5. Click any line to fix words, then Copy or download TXT.

Tips for better results

• Record close to the speaker and away from music or traffic.
• Set the language yourself if the recording mixes languages.
• For long files, keep the tab open and your laptop plugged in.

Is it really private?

Yes. Your audio is read and transcribed by your own device. The only download is the open-source Whisper model, which your browser keeps for next time. Read the privacy policy for details.