[Free] 4 ways to easily transcribe with Google Docs

Dec. 27, 2023

[Free] 4 ways to easily transcribe with Google Docs | AI character transcription service - Mr. Transcription

Did you know that the Google Docs you use all the time has a "voice input (transcription)" function?

  • I want to transcribe it for free.
  • I always use Google Docs for work.
  • In addition to real-time audio transcription, I would like to try converting recorded data into text and extracting text from images and PDFs.

It's clearly a waste if you don't use these things!


I want to know everything you can do with Google Docs transcription!

This time, we will explain the transcription tools available in Google Docs for you.

Even if you search for information on transcription of Google Docs, it seems that in many cases only ``real-time voice input' ' or ``voice data text conversion'' methods are introduced, so there are many different methods in the article. We will cover and explain all the transcription-related functions.

We will introduce detailed steps for each purpose as clearly as possible, so please feel free to transcribe them for reference.

After reading this article, you will be able to easily perform various tasks such as creating audio sentences and transcribing meeting minutes using Google Docs, without having to install any new apps.

Please watch till the end.

[Free] 4 ways to easily transcribe with Google Docs


Now, I will explain four ways to easily transcribe text using Google Docs.

Real-time voice input

The easiest way to transcribe with Google Docs is "Real-time voice input" .

With real-time voice input, just speak into the microphone and your voice will be automatically transcribed into text .

Even with the same Google Docs, the operation method and interface (appearance) differ slightly depending on the OS, so I will explain the method for each OS.

Procedures for PC (Windows/Mac) version

First, here is the real-time voice input method when using Google Docs from a browser on a Windows or Mac computer.

1. Tools → Voice input (Ctrl+Shift+S/⌘+Shift+S)

1. Tools → Voice input (Ctrl+Shift+S/⌘+Shift+S)

2. Click on the microphone to start transcription (the microphone will turn red)

2. Click on the microphone to start transcription (the microphone will turn red)

mic turns red

3.Click the microphone again to finish

3.Click the microphone again to finish

Now you can input voice input on your computer from a browser such as Google Chrome.

iPhone version instructions

Next is how to input voice on iPhone.

On iPhone, input using the iPhone's built-in voice input instead of Google Docs voice input.

1. Tap the microphone button at the bottom of the software keyboard

1. Tap the microphone button at the bottom of the software keyboard

2. Waveform is displayed (transcription starts)

2. Waveform is displayed (transcription starts)

3. Tap the waveform to finish

3. Tap the waveform to finish

You can also use this method to transcribe text using Google Docs on your iPhone.

Android version instructions

Finally, here is the process of transcribing using Google Docs on an Android smartphone.

*This explanation uses Android 12 as an example.

1. Tap the microphone button on the software keyboard

1. Tap the microphone button on the software keyboard

2. The color of the microphone button changes and transcription starts

2. The color of the microphone button changes and transcription starts

3. Tap the microphone button again to exit

3. Tap the microphone button again to exit

Now you can transcribe with Google Docs.

Bonus: How to input punctuation marks and symbols

In addition to text, you can also input frequently used symbols by voice.

  • Period (.): Maru
  • Commas (,): Toten
  • Square brackets (“”): Square brackets/square brackets

There are many other keywords that you can enter, so please try them out.

Type by voice - Docs Editors Help
Dictate text on iPhone - Apple Support (Japan)
Type with your voice - Android - Gboard Help

How to transcribe audio and video using PC + Google Docs

The flow introduced above was a method of inputting what was said in real time.

In fact, if you use a Windows or Mac computer, with a little more effort, you can also transcribe recorded data using Google Docs.

Process of transcribing with Google Docs

The process of transcribing using Google Docs' functions is as follows.

  1. Set the stereo mixer function in advance
  2. Play audio/video data
  3. Click the microphone button in Google Docs (start transcription)

"Stereo mixer" is a function that allows a computer to recognize not only the audio input from the microphone but also the audio played within the device.

The required settings for Windows and Mac are very different, so we will explain them separately here.

Windows stereo mixer settings

Windows PC

For Windows, you can have Google Docs recognize the played audio by configuring the following settings.

1.Settings: System → Sound → Select Input and click "Manage sound devices"

Settings: System → Sound → Select Input and click "Manage sound devices"

2. Input device: select stereo mixer

Select stereo mixer

3.Click "Enable"

Click "Enable"

4. Return to the previous screen and select Input: Stereo Mixer

Return to the previous screen and select Input: Stereo Mixer

*If the stereo mixer does not appear, downloading and installing the "Realtek audio driver" from each PC manufacturer's website will often work.

Reference: "VB-Audio VoiceMeeter Banana" is also recommended for advanced settings.

VB-Audio VoiceMeeter Banana

It is difficult to master the software right away, but if you want to make more detailed settings, you can use the software called "VB-Audio VoiceMeeter Banana" , which allows you to recognize, record, and process the sounds being played on your PC. operations are possible.

VB-Audio VoiceMeeter Banana is donationware (software that solicits donations) that can be used for free.

It can do the same thing as the "virtual audio device" software for Mac introduced below , so if you are interested, we recommend checking it out.

VB-Audio VoiceMeeter Banana

Mac stereo mixer settings


Since Mac does not have a sound mixer function as standard ,

  • virtual audio device
  • audio mix app

You will need to prepare these two items yourself.

However, there is no need to worry as both have free apps .

Procedure for setting up the stereo mixer function on Mac

On a Mac, you can set up the stereo mixer function as follows.

1. Install Soundflower or Blackhole *



First, install the virtual audio device app .

Download and install both Soundflower and Blackhole from GitHub.

*Soundflower does not work well on M1 Mac, so we recommend using Blackhole, a similar "virtual audio device" app.



2. Install RadioCast (audio mix app)


Next, install the audio mix app RadioCast .

This can be installed from the Mac App Store.

3. Configure settings from System Preferences

*Here, we will explain using Soundflower.

First, configure the input and output settings .

  • Output: Soundflower (64ch)
  • Input: Soundflower (64ch)

Next , configure RadioCast .

  • Input: Soundflower (64ch) → Enable “Main” and “Aux 1”
  • Output Main: Soundflower (2ch)
  • Output Aux 1: Built-in output

You can now transcribe with Google Docs on your Mac.

However, as you can see from the flow I introduced , complex settings are required .

If you want smooth and easy transcription, we also recommend an AI transcription service like "Mr. Transcription" introduced below.

In the case of a smartphone, the played audio file is recognized by the microphone.


In the case of smartphones, there is no suitable stereo mixer app, so the only way to do this is to use the built-in microphone to recognize audio files played through the smartphone's speakers.

  1. Play recorded audio
  2. Transcription with Google Docs

However, in the case of smartphones, there is no suitable stereo mixer app, so the only option is to use the built-in microphone to recognize the audio files played through the smartphone's speakers, and this method will not work unless the audio data and playback environment are well-prepared. .

In such cases, we recommend using a dedicated transcription app, which we will introduce at the end of the article.

How to transcribe by scene using Google Docs

Next, we will explain transcription methods for each situation, such as extracting text from minutes, images, and PDFs.

Minutes (Zoom, Microsoft Teams, etc.)

Minutes (Zoom, Microsoft Teams, etc.)

If all the participants are present, you can transcribe everyone's audio simultaneously using the methods introduced above.

However, in the case of a web conference, even if only the person in charge of taking minutes turns on the voice input function, only the voice of the person in charge can be converted into text.

If you use the stereo mixer function, you can transcribe the audio from both the microphone and speaker at the same time, but there is an easier method, so I will introduce it.

Transcribe meeting minutes with Google Docs

Following this process, you can transcribe meeting minutes using Google Docs.

  1. Share the same document using the Google Docs sharing feature
  2. Participants launch the web conferencing tool and Google Docs on their respective devices.
  3. Start voice input (transcription) at the same time

However, be careful not to run into trouble as it is not intended to be used.

In the unlikely event that you are unable to transcribe the transcript properly, or to make it easier to edit later, use Zoom's recording function or prepare a separate recorder (smartphone) to preserve the audio data just in case.

Extract text from images/PDFs

  1. Upload images and PDF files to Google Drive
  2. Right click on file
  3. Open with app → Google Docs

By doing this, you can transcribe from images and PDFs with Google Docs.

The automatically transcribed text will be displayed along with the original image/PDF data.

There are four supported files: jpg, png, gif, and pdf (up to 2MB in size).

Convert PDF and photo files to text - Computer - Google Drive Help

What to do when you can't transcribe with Google Docs


If you speak into the microphone but are not transcribed, there are three possible causes:

  • Browser microphone permissions are not allowed on the PC
  • Smartphone voice input is not enabled

Each can be resolved in the following ways:

How to allow browser microphone permissions on PC

In Windows/Mac browsers (Google Chrome), microphone permissions can be granted in the following ways.

1. Select Privacy and Security from Google Chrome settings

Select Privacy and Security from Google Chrome Settings

2. Select permissions (microphone) from “Site settings”

Select permissions (microphone) from "Site settings"

3. Turn on "Allow sites to request the use of your microphone"

Turn on "Allow sites to request the use of your microphone"

How to enable voice input on your smartphone

You can enable voice input on iPhone and Android respectively by:


On iPhone, you can grant microphone privileges in the following ways.

1. Open "General" from the Settings app

Open "General" from the Settings app

2. Turn on “Voice input” from “Keyboard”

Turn on “voice input” from “keyboard”


*This explanation uses Android 12 as an example.

1. Open the Settings app

Open the Settings app

2. Open "Language & Input"

Open "Language & Input"

3. Select “Gboard” from “Screen keyboard”

Select “Gboard” from “Screen keyboard”

4. Select "Voice input" on the Gboard settings screen

Select “Voice Input” on the Gboard settings screen

5. Turn on voice input

Turn on voice input

If audio data is not transcribed even after playing it

If the audio data is not transcribed even after playing it, these are possible causes.

  • Stereo mixer is not turned on.
  • Browser is not active.

The second most common problem is that the browser is not active.

Please note that Google Docs will automatically stop transcription if another window is active .

When transcribing,

Play the audio data → click the start transcription button

It is difficult to make mistakes if you do them in this order, so it is recommended that you memorize them.

If the transcription accuracy is low

If Google Docs recognizes your voice but the transcription accuracy is low, these are possible causes.

  • small volume
  • There is noise
  • fast speed

For real-time audio input, we recommend holding your mouth close to the microphone, speaking slowly and clearly, and using a high-performance external microphone if possible .

When transcribing using recorded data, use an editing app such as Audacity to remove noise and adjust the volume and speed to improve the accuracy of the transcription.

If you are unable to transcribe successfully even after taking these measures, or if the transcription stops midway, you can use the other methods introduced below to transcribe smoothly.

4 recommended transcription services other than Google Docs

Finally, we will introduce a service that allows you to smoothly transcribe even in situations where you are not good at using Google Docs!

We recommend an AI transcription service.

You can easily and smoothly transcribe audio and video files that Google Docs is not good at.

1. Mr. Transcription

Mr. Transcription

If you are looking for a transcription service other than Google Docs, we recommend this one.

"Mr. Transcription" is a transcription service that uses the latest AI, and you can easily transcribe audio, video, images, and PDF files by simply uploading them.

Transcribing audio that has already been recorded using Google Docs requires the complicated steps introduced above , but with Mr. Transcription, you don't need to do that.

It's free, no registration or login required, and you can transcribe files up to 1 minute in length, so we recommend trying it out first.

2.Speechy Lite

Speechy Lite

Speechy Lite is the perfect app for easy transcription on your iPhone.

Transcribed text and recording data can be easily shared with other apps.

Speechy Lite



The Speechy Lite introduced above is only available for iPhone, so this app is recommended for Android users .

Symbols are supported by voice commands as well as keyboard shortcuts.




This is recommended if you want to transcribe English with high accuracy .

It is a service that specializes in English transcription, and can clearly distinguish between speakers even in conversations with multiple people, making it ideal as a meeting minutes tool.




This time, I explained the transcription function of Google Docs.

Although Google Docs is often treated as a replacement for Microsoft Word, it actually has many more useful functions than Word .

Why not use this article as a reference to make full use of its various functions?

Also, the transcription function is easy to use with a dedicated transcription service, so we recommend using it in conjunction with Google Docs!

■ AI transcription service "Mr. Transscription"

"Mr. Transcription" is an online transcription tool that can be used from zero initial cost and 1,000 yen per month (* free version available).

  • Supports more than 20 file formats such as audio, video, and images
  • Can be used from both PC and smartphone
  • Supports technical terms such as medical care, IT, and long-term care
  • Supports creation of subtitle files and speaker separation
  • Supports transcription in approximately 100 languages ​​including English, Chinese, Japanese, Korean, German, French, Italian, etc.

To use it, just upload the audio file from the site. Transcription text is available in seconds to tens of minutes.
You can use it for free if you transcribe it for up to 10 minutes, so please try it once.

It is "Mr. Transcription" who can easily transcribe from audio, video, and images. Transcription allows you to transcribe for up to 10 minutes for free. You can copy, download, search, delete, etc. the transcribed text. You can also create subtitle files, which is ideal for transcription of interview videos.
HP: mojiokoshi3.com
Email: mojiokoshi3.com@gmail.com
Related article