Nouplo

Transcribe audio to text

English recordings into a punctuated transcript and SRT subtitles, on your own device.

Drop files here

or click to choose from your deviceAccepted: MP3, M4A, AAC, WAV, OGG, OGA, OPUS, FLAC, WEBA, MP4, M4V, WEBM, MOV, MKV

One file per runUp to 150 MB per file5 runs per dayRemove limits with Pro✓ Works offline

Your files stay on your device

This tool runs entirely in your browser. Nothing is uploaded, nothing is stored, and you can even turn off your internet connection before you start.

Example

Example: a 25-minute interview recorded on a phone, with speakers and times

A local-history student recorded a 25-minute interview with a retired baker on her phone: interview.m4a, about 24 MB. She chooses English and “Transcript and SRT subtitles”, and ticks “Put the time at the start of each line” and “Separate the speakers”.

  1. The first time, the English model (about 78 MB) and the two speaker models (another 34 MB) download once; after that they start straight away.
  2. The recording is cut at its pauses, and each stretch is read on its own and becomes one line, with capitals and full stops written by the model.
  3. With speakers on, the recording is read a second time and the lines start with Speaker 1 or Speaker 2.
  4. On a computer, expect roughly 6 to 12 minutes for the words, and about twice that with speakers.
File What its first lines look like
interview.txt [00:00:02] Speaker 1: Thanks for seeing me. How long did you run the bakery?
[00:00:06] Speaker 2: Thirty-one years. We started with one oven and a bicycle.
interview.srt 1 · 00:00:02,400 --> 00:00:06,100 · Speaker 1: Thanks for seeing me. How long did you run the bakery?
2 · 00:00:06,900 --> 00:00:12,300 · Speaker 2: Thirty-one years. We started with one oven and a bicycle.

Two files, interview.txt and interview.srt. She replaces “Speaker 1” and “Speaker 2” with the two names using find and replace, then checks names, places and dates against the recording, where a speech model most often slips.

How it works

  1. Add an audio or video file: MP3, M4A, WAV, MP4 and most others a browser can play.
  2. Tick “Put the time at the start of each line” if you want timestamps in the transcript.
  3. Tick “Separate the speakers” for an interview or a meeting; each line then begins with Speaker 1, Speaker 2 and so on.
  4. Select Transcribe. The first time, the speech model (about 78 MB) downloads once; after that it starts straight away.
  5. Copy the transcript, or download it as a text file together with SRT subtitles.

Frequently asked questions

How accurate is it?
It uses Whisper base (OpenAI, Apache 2.0). On clearly read English (the LibriSpeech test set) it got about 5 % of words wrong in our tests. Accents, noise, people talking over each other and specialist words bring more mistakes; for noisy recordings, try Remove background noise first.
Does it add punctuation?
Yes. Whisper writes capital letters, commas and full stops itself. Each line of the transcript is a stretch of speech between pauses, and the subtitles are cut at the same places.
Can it tell the speakers apart?
Tick “Separate the speakers” and every line begins with Speaker 1, Speaker 2 and so on, which is what makes an interview or a meeting readable. The recording is then read a second time by two further models — one that finds where the voice changes, one that turns each stretch of speech into numbers standing for the voice — so the first run downloads another 34 MB and the wait roughly doubles. They are numbered rather than named because nothing in the recording says who anybody is; replacing “Speaker 1” with a name afterwards takes a moment. Two people recorded clearly come out right; one microphone in a meeting room, voices that sound alike and long stretches of people talking over each other are where it makes mistakes.
How long does it take?
On a computer, roughly a quarter to a half of the recording’s length. Phones are slower, and a long recording can run out of memory there; cut it into shorter parts first.
Can it do other languages?
Eight more — switch the language. Japanese is read by a model made for it; German, French, Spanish, Portuguese, Italian, Korean and Turkish by Whisper small, because base, which is good enough for English, made up to twice as many errors on them in our tests. That larger model is about 250 MB the first time.
How big a recording can I transcribe?
On the free plan, one file of up to 150 MB a run and 5 runs a day; Pro removes those limits. A 25-minute phone interview in M4A is about 24 MB, an hour of MP3 at 128 kbps about 58 MB. Long recordings take memory: on a phone, cut them into parts first.
Is my recording uploaded?
No. Recognition runs in this page, on your own device, which makes it suitable for meetings, interviews and other recordings that should not leave it. Once the model has downloaded, it also works offline.

Made for a specific use

Related tools

❝ Japanese speech to text Japanese recordings and videos into a transcript and SRT subtitles, without the audio leaving your device. ❝ Meeting recording to minutes Who said it, when they said it, and the headings ready for what you decide it meant. ▭ Add subtitles to video An SRT file burned into the picture, so the words show on every screen. ≋ Remove background noise from audio Fans, hiss and hum taken out from under a voice.