Supported Audio and Video Formats

TranscribeThis transcribes the spoken audio in most common audio and video files — including MP3, WAV, M4A, AAC, FLAC, OGG, Opus and WebM audio, and the audio track of MP4, MOV, MKV, AVI and other video. Every file is decoded to 16 kHz mono before recognition, so the container or "lossless" quality does not change accuracy on its own — a clean recording matters more than the format.

Upload any supported audio or video file

or drag & drop it here

MP3, WAV, M4A, MP4 and more · first 5 minutes free, no account

Up to 99% Accurate90+ Languages1-Hour Audio in 2 Min30+ File Formats

Limits at a glance

Guest (no account)	First 5 minutes transcribed, up to 50 MB
Free account	3 transcriptions/day, first 5 minutes each
Pro	Up to 2 GB / 5 hours per file
Business	Up to 5 GB / 8 hours per file
Video	The audio track is transcribed; on-screen text is not read
Processing	Upload-first — files are processed after upload, not live

Supported audio formats

TranscribeThis accepts the common audio containers and codecs used by phones, recorders, and editing tools:

MP3 — the most common compressed audio format
WAV — uncompressed audio (large files; not more accurate than a clean MP3)
M4A / AAC — used by iPhone Voice Memos and most modern recorders
FLAC, ALAC, AIFF, APE — uncompressed and archival formats
OGG, Opus, WebM — open web audio formats
WMA, AMR, 3GP, CAF, M4B — legacy and platform-specific formats

Why format ≠ accuracy

Every upload is decoded to 16 kHz mono audio before recognition. A big uncompressed WAV does not transcribe better than a clean MP3 of the same recording — microphone quality, background noise, and speaker distance decide accuracy, not the file extension.

Supported video formats

For video, TranscribeThis extracts and transcribes the audio track. It does not read on-screen text or describe visuals.

MP4 / M4V — the most common video containers
MOV — Apple / QuickTime video
MKV, AVI, WMV, FLV — other common containers
MPEG / MPG, 3G2 — legacy formats

You can also paste a YouTube link (transcribed from the video's existing captions, which are segment-level rather than word-level). Signed-in users can import from Google Drive and Dropbox links.

Export formats

Once a transcript is ready you can export it in five formats. Full export is a paid feature; the free tier gives a preview.

Format	Use it for
TXT	Plain text for notes and search
DOCX	An editable document
PDF	A fixed, shareable copy
SRT / VTT	Timed captions to review (a draft, not finished styled subtitles)

Size and length limits

Limits depend on your plan. If a file is larger than your plan allows, export it at a lower bitrate or split it before uploading — this does not reduce accuracy, since audio is downsampled anyway.

Note

The free tier transcribes only the first 5 minutes of any file, regardless of the file's total length.

Frequently Asked Questions

What audio formats can I transcribe?

MP3, WAV, M4A, AAC, FLAC, OGG, Opus, WebM, WMA, AMR, AIFF, ALAC and more.

Can I transcribe a video file?

Yes — the audio track of MP4, MOV, MKV, AVI, WMV and similar files is transcribed. On-screen text is not read.

Does a WAV or FLAC give a more accurate transcript than an MP3?

No. All files are decoded to 16 kHz mono before recognition, so a clean MP3 transcribes just as well. Recording quality matters, not the container.

What is the largest file I can upload?

Guests: 50 MB. Pro: up to 2 GB / 5 hours. Business: up to 5 GB / 8 hours per file.

My format isn't listed — what do I do?

Re-export or convert it to a common format like MP3 or WAV, then upload. Avoid unnecessary re-compression of the original.

Related resources

How to transcribe audio

Reviewed by the TranscribeThis product team · Last updated: July 2026