About Speech to Text
Speech to Text lets you type with your voice. Press the microphone, start talking, and your words appear in real time. Say "comma", "period" or "new paragraph" to format as you go.
How it works
The tool uses your browser's built-in speech recognition (the Web Speech API). Audio from your microphone is turned into text by your browser's speech service, and results appear word by word. The tool then turns spoken punctuation commands into the matching symbols and line breaks, and can capitalize the start of each sentence automatically.
Browsers stop listening after a period of silence. The tool restarts recognition automatically, so you can pause to think and carry on without pressing anything until you click Stop.
Voice commands (English)
- "comma", "period" or "full stop", "question mark", "exclamation mark", "colon", "semicolon"
- "new line" starts a new line, and "new paragraph" leaves a blank line.
Spoken punctuation also works when you dictate in French, Spanish, German or Arabic: say the punctuation in that language, for example "virgule", "coma", "Komma" or "فاصلة".
What you can use it for
- Writing faster: most people speak about three times faster than they type.
- Drafting emails, articles, notes and ideas while they're fresh.
- Accessibility: for people with RSI, injuries or difficulty typing.
- Practicing pronunciation in a language you're learning.
Tips for the best results
- Select the right language and accent, for example English (UK) or English (India).
- Use a headset or a quiet room. Background noise is the biggest cause of mistakes.
- Speak naturally in full sentences. Recognition uses context, so whole phrases work better than single words.
- Dictate first and edit afterwards. Stopping to fix every word breaks your flow.
Privacy note: this website never records or stores your audio. However, in Chrome and Edge the browser sends audio to Google's or Microsoft's speech service for transcription. Safari can recognize speech on your device.