Guide

Transcribe MP3 to text

Upload an MP3 and the transcript comes back with a start and an end time on every line, speaker labels on request and six export formats. One file is up to 64 MB and 120 minutes: at 64 kbps that is a two-hour recording, at 128 kbps it is about an hour. The free plan is $0 with 3 files a day, Pro is $10 a month when you pay yearly ($120 a year).

Updated 2026-10-21 · Author: Mark Vesyoly · 6 minutes

What you get for an MP3

Everything in this table is a number we can defend: it comes from the service contract, from the pricing page, or from a measurement we ran ourselves.

Transcribing an MP3 with Transcrib Si: prices, limits and output
WhatValueWhere it comes from
The file we take MP3 and the other containers: wav, m4a, aac, flac, ogg, wma; video containers mp4, webm, mov Service contract
Size of one file 64 MB Service contract
Length of one file 120 minutes (two hours) Service contract
What comes back the text, plus a start and an end time for every segment; speaker labels on request Service contract
Export formats 6 — TXT, Markdown, SRT, VTT, CSV, DOCX (DOCX is a Pro feature) Pricing page
Free plan $0, 3 files a day, files up to 30 minutes, no card Pricing page
Pro $10 per month billed yearly ($120 a year), or $20 per month billed monthly Pricing page
Pro allowance 1,500 minutes of audio per calendar month Pricing page
Speed 0.84 s to transcribe a short file, 0.39 s to detect its language our own measurement

How to transcribe an MP3 file

  1. Put the file on the page, or send it from your own code

    Drop the MP3 on the widget below, or send it with POST /v1/transcripts and a multipart file field. One file, up to 64 MB and 120 minutes.

  2. Set the language, or let the service detect it

    Choose Russian or English in the widget, or leave it on automatic detection — 0.39 s on a short file in our own measurement. The API takes the same choice in the language field: ru, en or auto.

  3. Ask for speaker separation when there is more than one voice

    Switch on “Split by speaker” and the people in the recording are told apart. The API takes the same switch in the diarize field.

  4. Read it, fix a word, export it

    Every segment carries its start and end time. Correct a name in the editor, save, and export to TXT, Markdown, SRT, VTT, CSV or DOCX.

How much MP3 fits in 64 MB

The sizes below are calculated from the bitrate, not measured on a file. The limit that usually decides is the size, not the length.

How much audio fits in the 64 MB limit, calculated from the bitrate
RecordingSize (calculated)Fits 64 MB?
10 minutes at 64 kbps 4.8 MB yes
60 minutes at 64 kbps 28.8 MB yes
120 minutes at 64 kbps 57.6 MB yes
10 minutes at 128 kbps 9.6 MB yes
60 minutes at 128 kbps 57.6 MB yes
120 minutes at 128 kbps 115.2 MB no — the file is refused

MP3, M4A or WAV: which one to upload

The formats we take and where they come from
FormatWhere it comes fromWhat to know
MP3 voice recorders, podcast downloads, anything exported to MP3 the smallest choice at the same quality; 64 kbps is enough for speech
M4A / AAC iPhone Voice Memos, the Android recorder, messenger voice notes the same engine; the page on M4A explains how to get the file off the phone
WAV studio exports, dictation apps, hardware recorders big: 16-bit 16 kHz mono is about 32 KB a second, so ten minutes is about 19 MB
MP4 / MOV / WebM screen recordings, conference recordings, video the picture is not read; a long video usually has to lose its picture first
OGG, FLAC, AAC, WMA everything else we accept one file at a time, up to 64 MB and 120 minutes

What we do not do

We do not convert a folder of files in one go, we do not download anything from a link, and we do not change the audio: an MP3 goes in and text comes out. For a batch of episodes, see the plan for committed volume.

Try it now

Put a file on the page and read the first lines.

The widget below is the same one as on the home page: file → transcript with timecodes and speakers → export. The transcript is saved to your account.

Drop an audio or video file

or — mp3, wav, m4a, mp4, up to 64 MB and two hours

No account yet? The free plan needs no card. Create a free account or sign in.

FAQ

Questions this page answers.

Can I upload a whole folder of MP3s at once?

One file per request. A folder of forty episodes is forty requests, and each one is its own transcript with its own times. On the Team plan a committed volume is written down in advance.

What bitrate do I need for speech?

64 kbps mono is enough for speech, and it is the only bitrate at which a two-hour recording fits the 64 MB limit. A higher bitrate only helps if the recording itself is noisy.

Does the MP3 quality change the transcript?

Yes, and it sets the ceiling: a 64 kbps mono recording of a noisy room loses more than the engine does. The engine reads what is in the file.

How long does it take to transcribe an MP3?

On a short file our own measurement was 0.84 s for the transcription and 0.39 s for the language detection. Longer files take longer: the engine works in 22-second fragments with a 3-second overlap, so a two-hour file is a few hundred fragments. We do not promise a fixed speed on a busy queue.

Can I get subtitles out of an MP3?

The MP3 has no picture, so what you get is a transcript with timecodes: SRT and VTT are two of the six export formats. For a video file, see the guide on MP4.

Is the free plan enough for MP3 files?

Free is $0 with 3 files a day and files up to 30 minutes, with timestamps, speaker labels and five export formats. No card and no trial clock.

Keep reading

Related pages.

Transcribe M4A to text

The format your phone records in, and how to get the file off it.

Transcribe MP4 to text

Video files, subtitles and the size limit.

Transcribe a podcast to text

Episodes, show notes and chapters.

Pricing

Every plan, every limit, in one table.

Open the app

Upload with drag and drop, the queue and the exports.

FAQ

The live answer base: 99 questions about the price, the limits, the languages, the exports, the privacy and the API, each with the page of this site it comes from.

Written by a person

Mark Vesyoly, Founder.

Every number on this page comes from the service contract, the pricing page or our own measurements. The author of the page and the publisher of the site are the same person. Questions and corrections: support@transcrib.si.