How to transcribe audio to text

Transcribing audio means turning the speech in a recording into written text, either by typing it as you listen or with speech-to-text software that you then check. A usable transcript has four things:

A silver microphone, a vintage radio and headphones on a wooden table
A microphone and headphones, the tools for turning a recording into text.Photo: StockSnap / Pixabay
  1. 1

    Every word, in order

    What was said, as said, not a summary.

  2. 2

    Who said it

    A speaker label on each turn when more than one person talks.

  3. 3

    Timestamps

    So you can find any line in the recording again.

  4. 4

    A check pass

    Names, numbers and unclear words verified against the audio.

Transcribe it in Evernote. Drop in a recording and get a transcript with speakers, then ask for any quote.

Transcribe your recording in Evernote

How to transcribe audio to text in 7 steps

  1. 1

    Start with the clearest file

    Use the original recording, not a copy of a copy. If you are still recording, put the microphone close to the speaker and away from noise.

  2. 2

    Choose how to transcribe

    Type it yourself for short, sensitive or very noisy audio. For anything longer, let speech-to-text software do a first draft, then check it.

  3. 3

    Upload the file

    In Evernote, add the file to a note and choose to transcribe it. Evernote accepts common audio files such as MP3, M4A and WAV.

  4. 4

    Turn on speaker labels

    For interviews and meetings, ask the tool to identify who said what. Rename the speakers once, and the names carry through the transcript.

  5. 5

    Keep timestamps

    A timestamp at the start of each turn lets you jump back to check a line or pull a quote.

  6. 6

    Check names, numbers and unclear words

    Listen again wherever the text looks wrong. Mark what you can't make out, for example [inaudible 12:05].

  7. 7

    Add sounds that matter

    A basic transcript includes non-speech audio needed to understand the content, such as [laughter] or [phone rings].

Example transcript

An interview with a library director, 38 minutes
TimeSpeakerWhat was said
402:10YouHow did the funding cut change the library?
514:52Ana RiveraWe lost a third of our budget in one vote, and the first thing to go was Sunday hours.
617:40Ana RiveraThe council voted 5 to 2. [inaudible 17:48] was the only one who asked about the kids.
721:30Ana RiveraKids were doing homework in the parking lot, just to use our Wi-Fi. [laughs]

Speaker names, timestamps at the start of each turn, unclear words marked with the time.

Ways to transcribe audio

Each option trades time against accuracy and cost. Checks are on each maker's own help pages, November 2026.

MethodWhat you doGood to know
By handListen, pause and typeFree and private, but slow
iPhone Voice MemosRecord, then view or copy the transcriptiPhone 12 or later, 10 languages
Word for Microsoft 365Upload a WAV, MP4, M4A or MP3 file to TranscribeWindows, commercial; 300 min a month
EvernoteAdd the file to a note and transcribe itSpeaker labels, timestamps, language detected or chosen
ChatGPTAttach an audio file and ask for a transcriptAudio uploads need a paid ChatGPT plan; up to 6 minutes per pass

Sources: Apple Support, Microsoft Support, OpenAI Help Center.

Free transcript format

Copy it, or save it to your Evernote account and use it for every transcript you clean up.

Recording: [file name], [date], [length]

Speakers: [name] (host), [name] (guest)

[00:00] [Speaker]: [what was said, word for word]

Unclear: [inaudible mm:ss] or [crosstalk mm:ss]

Sounds that matter: [laughter], [music], [phone rings]

Checked by [name] on [date]: names, numbers, quotes

Trusted by Millions Worldwide

4.4

2,100+ reviews on G2

4.4

8,200+ reviews on Capterra

4.4

73,000+ reviews on App Store

248M

Registered users

Transcription questions

How do I transcribe audio to text for free?

Type it yourself, or use a tool already on your device. iPhone Voice Memos shows a transcript of recordings on iPhone 12 or later, and Google Docs voice typing turns live speech into text in Chrome, Edge or Safari.

How long does it take to transcribe audio by hand?

Longer than the recording itself, because you pause and rewind. You can let software make a first draft and spend your time checking it.

Can Word transcribe audio?

Yes. Word for Microsoft 365 on Windows in commercial tenants can transcribe uploaded WAV, MP4, M4A and MP3 files, up to 300 minutes a month with a Microsoft 365 subscription.

Can ChatGPT transcribe audio?

Yes. You can attach an audio file and ask for a transcript; audio uploads are available on paid ChatGPT plans, up to 6 minutes per pass. OpenAI notes that transcription can contain mistakes, so check important parts.

How do I transcribe an interview with two people?

Use a tool that labels speakers, such as Evernote's "Identify who said what", then rename the speakers. Keep a timestamp at the start of each turn so you can check quotes.

What is the difference between a transcript and captions?

Captions are timed text that shows on the video as people speak. A transcript is the full text, read separately, and can include speaker names and sounds.

Do I need permission to record and transcribe someone?

Rules on recording other people vary by place. Ask for consent before you record, and check the law where you and they are.

How accurate is automatic transcription?

It depends on the audio. Check names, numbers and anything you will quote against the recording.

How to transcribe audio to text with Evernote

Put the recording in a note, and Evernote writes the transcript under it, with who said what.

  1. 1

    Drop in the recording.

    Add an audio or video file to a note and choose to transcribe it. Turn on 'Identify who said what' to get speaker labels and timestamps.

  2. 2

    Find the quote.

    Ask the AI Assistant where a topic comes up and for the exact words. It reads the transcript and answers with the timestamp.

  3. 3

    Get the key points.

    Ask the Assistant to summarize the recording, for example as key points, and the summary appears above the transcript.

  • You can also rename speakers, so "Speaker 2" becomes the person's name throughout.
  • You can also transcribe only part of a long recording by choosing a time range.
  • You can also pick the language, or let Evernote detect it.

Turn any recording into text you can use

Drop in the file, get a transcript with who said what, then ask the AI Assistant for the quote or the key points.

Start for free