How do I change my voice-to-text settings?

Voice-to-text, also known as speech recognition or speech-to-text, is technology that allows users to dictate speech which is then transcribed into text. Rather than manually typing, users can speak into a microphone and their words will be converted into text. This technology is powered by machine learning algorithms that analyze speech patterns to identify words and phrases.

There are many reasons why someone may want to customize their voice-to-text settings. The default options may not always accurately capture an individual user’s speech patterns, pronunciation, or typing preferences. By making adjustments within the voice-to-text settings menu, users can personalize the experience so transcription is faster, more accurate, tailored to their needs, and enables greater productivity.

Accessing Voice-to-Text Settings

The voice-to-text settings on your device allow you to customize how text is dictated and transcribed from your voice. Here’s how to access these settings on different operating systems:

On Android devices, open the Settings app and select System > Languages & input. Look for “Google Voice Typing” and select Voice input for the keyboard you want to customize voice typing for, such as Gboard. This will open options to change the speech language, toggle voice typing on/off, and access additional settings like automatic punctuation insertion.

On iOS devices, open the Settings app and select General > Keyboard. Toggle on Enable Dictation to activate voice typing. Additional options like language selection, automatic punctuation, and command shortcuts can be configured under the Keyboards section.

For Windows 10 and 11, open Settings > Time & language > Speech. Turn on or off the Dictate button in the Speech toolbar section. The Voice typing menu provides options to select a speech language and link accounts.

On Mac computers, open System Preferences > Keyboard > Dictation tab. Check Enable Dictation to turn on voice typing dictation. The Language drop-down allows you to set the transcription language.

Most platforms provide quick access to voice typing settings from the onscreen keyboard. Look for a microphone icon while in a text field, then select the settings icon or menu to customize options.

Changing the Language

To change the language that voice-to-text recognizes and uses for transcription, you need to update the speech and language settings. On Android devices, go to Settings > System > Languages & input > Virtual keyboard > Google voice typing. Tap Languages and select the language you want it to recognize. On iPhones, go to Settings > General > Keyboard > Keyboards > Add New Keyboard and select the language. On Windows, go to Settings > Time & Language > Speech and change the default speech language. You may also need to update the Windows display language if you want voice-to-text to type in that language.

The language options available will depend on the platform. Some common languages supported across platforms include English, Spanish, French, German, Italian, Japanese, and Mandarin Chinese. Make sure to select the dialect as well for languages like English which have variations such as US English, UK English, etc. This will allow voice-to-text to accurately recognize accents and dialects.

Once you update the speech language, any voice input will be transcribed into that language. This allows you to seamlessly switch between languages without having to manually change any settings each time.

Using a Different Voice

You can change the default voice used for text-to-speech in your phone’s accessibility settings. Android and iOS both offer a variety of voice options to choose from. On Android, open your Settings app and go to Accessibility > Text-to-speech output (1). On an iPhone, go to Settings > Accessibility > Spoken Content > Voices (2).

Both operating systems let you preview each voice option before selecting it. Android has over 90 voices in 30 languages available. iOS offers a more limited selection of voices, but they include high-quality voices that sound very natural. Take your time sampling the different voices – consider pitch, cadence, gender, and language when picking one. Choosing a voice that’s clear and pleasant to listen to can greatly improve the text-to-speech experience.

Some third-party text-to-speech apps like NaturalReader (3) also let you import custom voices for an even wider selection. Paid voices generated from real voice actors often sound more human-like. With the right voice selected, listening back to passages of text can feel almost like having the words spoken aloud to you.

Sources:
(1) https://support.google.com/accessibility/answer/11221616?hl=en
(2) https://mcmw.abilitynet.org.uk/how-to-change-the-language-and-voice-used-for-text-to-speech-tts-in-android-13
(3) Example third-party app

Adjusting Speech Rate

The speech rate controls how fast or slow the voice-to-text feature speaks your words out loud. A faster rate can help you quickly transcribe long passages, while a slower rate gives you more time to review each word.

To adjust the speech rate on an iPhone or iPad:

Open the Settings app and tap Accessibility.

Select Spoken Content.
Drag the Speaking Rate slider left to slow down the rate or right to speed it up.

On Mac:

Go to System Preferences > Accessibility.
Click Speech.
Adjust the Speaking Rate slider as desired.

You can test out different speeds to find the optimal rate for your needs. The voice-to-text speech can be adjusted from very slow to very fast. Set it to a pace that’s comfortable for you to understand and keep up with.

Adding Punctuation

One of the key benefits of voice-to-text is having punctuation automatically inserted as you speak. This saves you time and effort compared to manually typing and punctuating text. However, the accuracy of automatic punctuation insertion can vary across voice-to-text services.

For Google’s speech recognition services like Voice Typing in Gboard and Google Docs, punctuation is automatically added without any voice commands needed. According to Google Support, “Punctuation is automatically added as you speak.” [1] You simply speak naturally with pauses, and the service inserts commas, periods, question marks, and other punctuation.

Other Android voice typing services may require you to say punctuation commands out loud like “period” or “comma.” Check your device or app’s speech recognition settings to customize auto-punctuation behavior. For more finicky punctuation not dictated, you can always manually type it or edit the text later.

On iOS, auto-punctuation behavior varies by app. Apple’s built-in dictation feature does not automatically insert punctuation by default. You must enable a setting to insert stops and commas automatically when dictating. Third-party iOS apps like SpeechTeXter have more advanced punctuation insertion as you dictate.

Testing different voice-to-text services is the best way to find one that correctly punctuates with minimal effort on your part. Evaluate their auto-punctuation accuracy when speaking at normal and rapid speeds.

Capitalizing Words

One setting that can be adjusted related to voice-to-text is automatic capitalization of words. By default, most voice-to-text services will automatically capitalize the first word of each sentence as well as proper nouns.

On an iPhone, you can adjust automatic capitalization settings by going to Settings > General > Keyboard > Auto-Capitalization. There you can turn auto-capitalization on or off.

On Android devices, capitalization settings can be adjusted in Gboard app settings. Open the Gboard app, go to Settings > Text Correction > Auto-Capitalization and adjust as desired. Some Android devices also allow adjusting capitalization settings under Language & Input in main device settings.

For Google Docs voice typing, there is an option to manually capitalize words by saying “cap” before the word you want to capitalize. However, there is currently no setting to adjust automatic capitalization within Google Docs itself ¹.

On Windows devices, some users have reported random capitalization issues with voice typing that may require reporting as a bug to Microsoft ².

Adjusting automatic capitalization settings can help optimize voice-to-text accuracy in sentence structure and proper nouns.

Enabling Profanity Filter

If you want to filter out profanity and explicit language from your voice transcriptions, you have a few options:

On Android devices using Gboard or Google Voice Typing, you can enable the profanity filter in your keyboard settings. Go to Settings > Languages & Input > Virtual Keyboard > Gboard > Text Correction. Toggle on “Block offensive words” to filter profanity.

For Google’s own Speech-to-Text API used by some apps, you can enable the profanity filter when initializing your speech client. As per Google’s documentation, “This will replace profane words in the transcript with a series of asterisks.”[1]

On Samsung Galaxy devices, open Settings > General Management > Language and Input > On-screen Keyboard > Samsung Keyboard Settings. Toggle on “Block offensive words” to filter profanity.

Third party apps like Otter.ai also allow you to enable profanity filtering in the settings. This will censor curse words with asterisks in transcriptions.

So in summary, most voice-to-text services give you the option to enable profanity filtering to block offensive language. Check your keyboard settings or speech client initialization to turn this on.

Using Voice Commands

One way to further enhance and optimize the voice-to-text experience is by using voice commands. Voice commands allow you to control certain functions and features hands-free, which can greatly improve workflow. According to Microsoft Support, Windows 10 includes a built-in voice command feature. Some examples of voice commands you can use include:

“Select all” – highlights all text
“Cut selection” – cuts highlighted text

“Copy selection” – copies highlighted text
“Paste” – pastes copied or cut text
“Undo that” – undoes your last action

“Start dictation” – starts the dictation feature
“Stop dictation” – ends the dictation session

Using these kinds of voice commands can help optimize the voice-to-text experience by enabling common functions hands-free. This allows you to stay focused on the content instead of having to stop to manually highlight or copy/paste text.

Additional Customization Options

Voice-to-text software often provides additional ways to customize the experience beyond just language and voice selection. Here are some other useful settings to check:

Custom words – Add specific words or phrases that the software may not recognize by default, like people’s names or industry-specific terminology.
Change default start/stop commands – If you don’t want to use the default “Start Recording” and “Stop Recording” commands, some apps allow changing these hot words.

Enable/disable automatic punctuation – Turn on or off whether you want punctuation like periods, commas, and question marks to be added automatically.
Capitalization options – Choose whether to auto-capitalize words after punctuation, never auto-capitalize, or only capitalize proper nouns.
Keyboard shortcuts – Set custom keyboard shortcuts for common commands to optimize your workflow.

Interface themes – Pick light or dark mode, customize colors, or enable high contrast themes.
Cloud syncing – Sync custom words, commands, and preferences across devices.

Taking the time to explore and tweak these additional settings can help you optimize voice-to-text to suit your personal preferences and usage style.