Turn audio & video into clean text.
Transcribe audio and video files for free directly in your browser with Whisper. Upload your media, generate text, copy your transcript, or download it as a TXT file.
Transcribe a file
Upload audio or video
MP3, WAV, M4A, MP4, WEBM and other browser-supported media.
How free transcription works
Convert audio or video to text in three simple steps.
Choose your media
Select an audio or video file stored on your computer or phone.
Transcribe with Whisper
The speech model runs in your browser. The first use can take longer while the model is downloaded.
Copy or download
Edit the generated transcript, copy the text, or save it as a TXT file.
Other Free Tools
Use our growing collection of browser-based tools for images, PDFs and Word documents.
HEIC to JPG
Convert iPhone HEIC photos to JPG.
HEIC to PDF
Convert HEIC photos to PDF.
JPG to HEIC
Convert JPG images to HEIC.
Remove Background
Remove a single image background and download a transparent PNG.
Bulk Background Remover
Process multiple images in one batch and download all results as ZIP.
Document Scanner
Scan a document from your camera or gallery and download it as PDF or JPG.
JPG to PDF
Combine JPG and PNG images into one PDF.
PDF to JPG
Convert each PDF page into JPG images.
Word to PDF
Convert DOCX, ODT, RTF or TXT documents into PDF.
Word to JPG
Render supported Word/document formats into JPG.
PDF to Word
Extract text from text-based PDFs into editable DOCX.
Frequently asked questions
Quick answers about the free browser transcription tool.
Is audio and video transcription free?
Yes. This version processes supported local media files in the visitor's browser and does not require a paid transcription subscription.
Are my audio and video files uploaded to the website?
The included transcription code processes the selected media in the browser. It does not intentionally upload the file to this WordPress website.
Which file types work best?
MP3, WAV, M4A, MP4 and WEBM are good choices. Actual support can vary by browser and by the audio/video codec inside the file.
Why can the first transcription take longer?
The browser needs to download the selected Whisper model the first time. Later visits may be faster when browser caching is available.