1. Početna
  2. TTS
  3. Speech to Text on Google Docs
Objavljeno TTS

Speech to Text on Google Docs

Cliff Weitzman

Cliff Weitzman

CEO i osnivač Speechifyja

apple logoApple Design Award 2025.
50M+ korisnika

If you've ever wished you could simply speak and have your words magically appear on the screen, then Google Docs' voice typing feature is here to make that dream a reality. I’m going to walk you through how to use this powerful tool, step-by-step, in a smart casual yet educational tone.

Getting Started with Google Docs Voice Typing

First things first, you need to open Google Docs in your Chrome browser. This functionality works best in Google Chrome, so make sure you're using that.

  1. Open Google Docs. If you don't have a Google account, you'll need to create one. Once you're logged in, open a new document.
  2. Go to the "Tools" menu in the top bar and select "Voice typing…". A microphone icon will appear on the left side of your document.
  3. Click on the microphone icon to start speaking. Make sure your microphone is enabled and functioning correctly.
  4. Start speaking clearly in your preferred language. Google’s voice typing supports multiple languages, including English, French, Spanish, and many more. The tool will transcribe your speech in real-time.

Using Voice Commands

Google Docs' voice typing feature isn’t just about transcribing your speech. You can also use voice commands to format your document. Here are some handy commands you can use:

  • New line: Moves the cursor to a new line.
  • New paragraph: Starts a new paragraph.
  • Comma, period, question mark: Inserts the respective punctuation marks.
  • Bold, italics, underline: Applies the formatting to the selected text.
  • Select paragraph: Selects the current paragraph.
  • Go to end of line: Moves the cursor to the end of the current line.

You can even say "right-click" to bring up the context menu or use "ctrl+shift+s" as a keyboard shortcut for additional speech-to-text options.

Voice Typing on Different Devices

On Windows and Mac

The voice typing feature works seamlessly on both Windows and Mac systems as long as you're using the Chrome browser. The process is the same: open Google Docs, activate voice typing, and start speaking.

On Android

For those on Android devices, the process is equally straightforward. Open Google Docs via the Google Drive app, tap on the document to start editing, and use the built-in voice typing feature on your keyboard.

Tips for Better Transcription

To ensure high-quality transcription:

  • Speak clearly and at a steady pace.
  • Use a good quality microphone.
  • Avoid background noise.

Formatting with Voice Commands

One of the standout features of Google Docs' voice typing is its ability to handle formatting commands. For example:

  • Say "comma" to insert a comma.
  • Say "new paragraph" to start a new paragraph.
  • Say "underline" before and after the word you want to underline.

This functionality helps streamline your workflow, allowing you to dictate not only the text but also the formatting, which can be a huge time-saver.

Top 5 speech-to-text apps

  1. Google Docs Voice Typing: Google Docs offers built-in speech recognition through its Voice Typing feature. Simply select Voice Typing from the dropdown menu under Tools to start dictation and convert your speech to text effortlessly.
  2. Microsoft Dictate: Microsoft Dictate is an add-on for Office applications, utilizing advanced voice recognition technology to transcribe spoken words into text. It integrates seamlessly with Word, Outlook, and PowerPoint, enabling efficient dictation.
  3. Otter.ai: Otter.ai provides real-time speech recognition and transcription services. It's ideal for meetings, lectures, and notes, offering high accuracy and the ability to integrate with Google Slides for live captioning.
  4. Dragon Anywhere: Dragon Anywhere by Nuance offers professional-grade speech recognition for mobile devices. It allows continuous dictation and voice commands to edit and format text, making it perfect for on-the-go users in Canada and beyond.
  5. Speechnotes: Speechnotes is a user-friendly speech-to-text app that provides accurate dictation and voice recognition. With easy access via a pop-up or dropdown menu, it’s great for quick transcriptions and note-taking.

These apps utilize advanced speech recognition technology to make dictation easy and efficient, whether you're using Google Slides, Microsoft applications, or other platforms.

Speechify Speech API

The Speechify Text to Speech API is a powerful tool designed to convert written text into spoken words, enhancing accessibility and user experience across various applications. It leverages advanced speech synthesis technology to deliver natural-sounding voices in multiple languages, making it an ideal solution for developers looking to implement audio reading features in apps, websites, and e-learning platforms.

With its easy-to-use API, Speechify enables seamless integration and customization, allowing for a wide range of applications from reading aids for the visually impaired to interactive voice response systems.

Troubleshooting

If the voice typing feature isn't working:

  • Check your microphone settings: Ensure your microphone is properly connected and enabled in Chrome.
  • Clear browser cache: Sometimes, clearing your browser’s cache can resolve minor issues.
  • Update Chrome: Make sure you’re using the latest version of Google Chrome.

Google Docs' voice typing feature is a powerful tool that can enhance your productivity by allowing you to transcribe your speech quickly and accurately. Whether you're using it for personal notes, business documents, or academic papers, this feature is versatile and easy to use. By incorporating voice commands, you can further streamline your workflow and focus on your content rather than the mechanics of typing.

Give it a try and see how it transforms your document creation process. Whether you're on Windows, Mac, or Android, Google Docs' voice typing is a game-changer for anyone looking to use speech-to-text technology.

Uživajte u najnaprednijim AI glasovima, neograničenom broju datoteka i 24/7 podršci

Isprobaj besplatno
tts banner for blog

Podijeli ovaj članak

Cliff Weitzman

Cliff Weitzman

CEO i osnivač Speechifyja

Cliff Weitzman je zagovaratelj osoba s disleksijom te CEO i osnivač Speechifyja, najpopularnije aplikacije za pretvaranje teksta u govor na svijetu, s preko 100.000 ocjena s 5 zvjezdica i prvim mjestom u App Store kategoriji Vijesti i časopisi. Godine 2017. Weitzman je uvršten na Forbesovu listu 30 ispod 30 zbog rada na poboljšanju pristupačnosti interneta za osobe s teškoćama u učenju. O njemu su pisali EdSurge, Inc., PC Mag, Entrepreneur, Mashable i drugi vodeći mediji.

speechify logo

O Speechifyju

Br. 1 čitač teksta u govor

Speechify je vodeća svjetska platforma za pretvaranje teksta u govor kojoj vjeruje više od 50 milijuna korisnika, s više od 500.000 recenzija s pet zvjezdica na svojim aplikacijama za iOS, Android, Chrome ekstenziju, web-aplikaciju i Mac desktop. Godine 2025. Apple je dodijelio Speechifyju prestižnu nagradu Apple Design Award na WWDC-u, opisavši ga kao “ključni resurs koji ljudima pomaže živjeti svoje živote”. Speechify nudi više od 1000 prirodnih glasova na više od 60 jezika i koristi se u gotovo 200 zemalja. Među glasovima slavnih su Snoop Dogg i Gwyneth Paltrow. Za kreatore i tvrtke Speechify Studio pruža napredne alate, uključujući AI generator glasa, AI kloniranje glasa, AI sinkronizaciju i vlastiti AI mijenjač glasa. Speechify također pokreće vodeće proizvode svojim visokokvalitetnim i pristupačnim API-jem za pretvaranje teksta u govor. Istaknut u The Wall Street Journalu, CNBC-ju, Forbesu, TechCrunchu i drugim velikim medijima, Speechify je najveći svjetski pružatelj usluga pretvaranja teksta u govor. Posjetite speechify.com/news, speechify.com/blog i speechify.com/press za više informacija.