How to convert MP4 to text free (with speaker labels)

By Alex Topilski, Founder

2026-11-02

A one-hour Zoom or Teams call saved as MP4 contains roughly 7,000 to 9,000 spoken words - around 25 to 30 pages of text. Typing that back manually takes 3 to 5 hours at average typing speed. With WhoSayAh the same file returns a labelled transcript in a few minutes, free, with no account and nothing to install. You do not need to extract the audio first: drop the MP4 directly, set how many speakers were on the call, and the transcript arrives with each line attributed to the right voice. This guide covers every step and explains how to get the best result from whatever MP4 recording you have.

Step-by-step: upload your MP4 and get a transcript

1. Open the WhoSayAh home page and drop your MP4 onto it, or click to browse for the file. The upload starts immediately and a dialog appears showing the file name, size and detected length.
2. Check that the detected length looks right. Files up to 100 MB and 300 minutes are accepted per upload. If your recording is longer, see the section below on splitting files.
3. Set the language. Leave it on Detect automatically for most recordings. If the video is very short (under 2 minutes) or was recorded in a noisy environment, naming the language explicitly removes one source of error.
4. Switch on Label speakers if more than one person is talking. Enter the number of speakers if you know it - for a two-person call, entering 2 consistently produces tighter attribution than leaving detection open. If you are not sure, press I don't know - detect it.
5. Press Transcribe. Lines appear as they are processed, so you can start reading before the file is fully done.
6. Once the transcript finishes, press Name speakers. Each voice is shown with how long it spoke and its first line - for a call you attended, that is usually enough to identify who is who at a glance. Replace Speaker 1, Speaker 2 with real names and the labels update across the entire transcript instantly.
7. Copy to clipboard or download as .txt or .vtt.

Free, no account, no watermark on the output - up to 100 MB and 300 minutes per file.

Why you do not need to extract audio from an MP4 first

A common misconception is that only audio files can be transcribed - that an MP4 must first be converted to MP3 or WAV before uploading. That step is unnecessary. WhoSayAh accepts MP4 containers directly: only the audio track is read, and the video data is ignored entirely. This means a screen recording from OBS, a downloaded Zoom local file, a Teams meeting export, or a recorded webinar all upload as-is with no pre-processing on your end.

Skipping the extraction step also avoids a quality penalty. Every lossy re-encode - for example, demuxing an MP4 to AAC and then converting that to MP3 - introduces a small amount of irreversible compression noise. Starting from the original MP4 gives the transcription the cleanest possible signal.

What formats WhoSayAh accepts alongside MP4

MP4 is the dominant format for exported meeting recordings and screen captures, but WhoSayAh accepts several other containers and audio formats. If your recording came out as something other than MP4, you can upload it directly without converting.

The per-file limits are 100 MB and 300 minutes. A typical 1-hour Zoom recording in 720p MP4 runs between 150 MB and 400 MB; at 1080p it can reach 600 MB or more. If your recording exceeds the size limit, the section below explains how to split it without re-encoding.

Longer recordings: splitting an MP4 over the limit

A full-day training session or a long deposition will exceed the per-file limits. The practical fix is to split the video into segments under 300 minutes each before uploading. Free tools that do this without re-encoding the video - so no quality loss and fast operation - include:

• FFmpeg - one command splits an MP4 at an exact time marker with no re-encode (-c copy). Available on Windows, macOS and Linux. The fastest option for anyone comfortable with a terminal.
• VidCutter - a free GUI built on FFmpeg. Set in and out points visually, export each segment. No re-encode by default.
• Avidemux - open the file, select the segment range, and export with the copy codec. Available on all platforms; handles MP4, MKV and MOV.
• HandBrake - primarily a transcoder, but the chapter range option can cut a file to a time segment. Note that HandBrake re-encodes by default, which is slower and introduces a quality step; set the codec to passthrough if splitting only.

When cutting a multi-person recording, split at a silence or a natural pause rather than mid-sentence. Speaker labels restart at Speaker 1 at the beginning of each segment, so name the speakers in each part separately and reconcile them when combining the transcripts.

How to get the best transcript from a meeting MP4

Recording quality is the dominant factor in transcript accuracy - it matters more than any setting you choose in the tool. For meeting recordings specifically, a few decisions made before or during the call have a large effect on the output:

• Use a headset or USB microphone. Built-in laptop microphones pick up keyboard noise, room echo and fan hum. A headset or external USB microphone captures your voice close to the source and reduces all three. For a two-person remote call, this is the single most effective improvement.
• Avoid overlapping speech. Crosstalk - two voices at once - is the hardest problem for both word accuracy and speaker attribution. Even 2 seconds of overlap can shift the next few lines to the wrong speaker. A brief pause before responding helps significantly.
• Enter the exact speaker count. For a meeting with 3 participants, entering 3 consistently outperforms the auto-detect. A wide-pitched voice or someone who changes pace sharply between calm and animated turns can register as 2 speakers. Entering the known count removes that ambiguity.
• Upload the original export, not a re-encoded copy. Each lossy conversion blurs consonants. If you have the original meeting recording and a compressed copy, upload the original.
• Name the language for short clips. Auto-detection works from the audio signal and has less to go on when a recording is under 2 minutes. For short clips, naming the language explicitly removes one potential source of error.

A recording that sounds clear to your own ear will produce an accurate transcript. A recording where you can hear what was said but have to strain - background noise, distant microphone, heavy room echo - will still transcribe, but expect more errors on short interjections and consonant clusters. For a detailed walkthrough of two-person recordings specifically, the interview transcription guide covers volume imbalance, bilingual conversations and other common edge cases.

Speaker labels: turning a video call into a structured record

A plain-text transcript of a 6-person meeting is nearly unusable as a reference: you can read every word and still not know who made the commitment, who raised the concern, or who gave the number. Speaker labels attach each line to the voice that spoke it, automatically, turning a wall of text into a structured record.

The labels arrive as Speaker 1, Speaker 2 and so on. After transcription, Name speakers shows each speaker alongside how long they spoke and their opening line - for a meeting you attended, that is usually enough to match voices to names at a glance. Enter real names and they propagate across every line of the transcript instantly, including the downloaded .txt and .vtt files.

For a 1-hour meeting with 4 participants, assigning names to speaker labels takes under 2 minutes. Doing the same job by listening back and annotating manually takes 3 to 4 hours. The general video transcription guide covers how speaker attribution works across different video formats and recording conditions.

Download formats: .txt and .vtt

Once the transcript is ready you have three ways to take it:

• Copy to clipboard - one click, the full transcript (speaker names and all) lands in your clipboard for pasting directly into a document, CRM, or email.
• .txt - plain text, one line per speaking turn, speaker name prefixed. Opens in any text editor. Use it for meeting notes, a research document, or an attachment. No proprietary format, no dependency on any software staying available.
• .vtt - WebVTT with start and end timestamps on every cue. Drop this directly into an HTML5 <video> element as a subtitle track, upload it to YouTube as a caption file, or import it into Premiere Pro, DaVinci Resolve or any editor that accepts external captions. No conversion step required; WebVTT is a W3C standard and works across tools without additional processing.

Teams that publish a large volume of recorded content - weekly call recordings, training videos, webinar archives - need more than one-at-a-time uploads. For a growing catalogue of video with captions, CrocOTT handles the VOD platform side: it keeps caption files synced with the catalogue and removes the per-file manual step. For creators working with recorded streams, clipping and subtitling workflows are covered by OverlayMax.

What happens to your MP4 after upload

The uploaded file is deleted as soon as the transcript is ready. The transcript itself is deleted after 24 hours. There is no account, so nothing links either to you personally. The privacy policy states exactly what is stored and for how long; the terms of use set out the per-file size and length limits in full.

If the recording contains material that cannot leave your own network - legal depositions, medical consultations, NDAs, anything subject to a data-residency requirement - the alternative is a self-hosted installation where the audio never reaches an external server. FastoCloud provides that infrastructure: processing runs inside your own environment, there is no per-minute fee, and the workflow for whoever uploads the file is identical to what is described above.

Frequently asked questions

Do I need to convert MP4 to MP3 before uploading?

No. WhoSayAh accepts MP4 directly. Only the audio track is read; the video data is ignored. Uploading the original MP4 is faster and avoids any quality loss from an intermediate conversion step.

What is the size limit for an MP4 file?

The limit is 100 MB and 300 minutes per file. A 1-hour 720p MP4 typically runs between 150 MB and 400 MB. If yours exceeds the limit, split it with FFmpeg or Avidemux using the copy codec - no re-encode, no quality loss.

How long does transcription take for a 1-hour MP4?

Typically a few minutes. The tool is asynchronous: you upload once, get a job ID, and lines appear as they are processed. You do not need to keep the tab focused - come back when it is done and the full transcript will be waiting.

Can it transcribe a Zoom, Teams or Meet MP4?

Yes. Meeting recordings from Zoom, Microsoft Teams, Google Meet, Cisco Webex and similar platforms all export as MP4 and upload directly. For platform-specific steps see the Zoom guide and the Teams guide.

What if I do not know how many speakers are in the recording?

Press I don't know - detect it. The tool estimates the speaker count from the audio. Results are good for most recordings; where a speaker has a very wide pitch range, the estimate may be one higher than the actual number. Entering the exact count when you know it gives consistently tighter attribution.

Is there a limit per day?

There is no account and no daily cap. The limits are per upload: 100 MB and 300 minutes per file. You can upload as many files as you like, one at a time.

Convert your MP4 now