Is my voice recorded or uploaded?

No. Speech recognition is performed locally by your browser's built-in Web Speech API. Your audio is processed on your device and never sent to any server.

Which languages are supported?

Most major languages are supported including English, Spanish, French, German, Italian, Portuguese, Japanese, Russian, Hindi, Chinese, Korean, and many others. Support depends on your browser and operating system.

Does it work offline?

Yes, in supported browsers. Chrome and Edge use on-device speech recognition models that work without an internet connection once loaded.

Can I download the transcription?

Yes. You can copy the transcribed text to your clipboard or download it as a plain text file. The text is formatted with timestamps if you enable that option.

Why isn't Firefox supported?

Firefox does not currently implement the Web Speech API for speech recognition. We recommend using Chrome, Edge, or Safari for the best experience.

← Back

Speech-to-Text

Speak and see your words appear instantly. Uses your browser's built-in speech engine — your voice never leaves your device.

Your voice is never sent to our servers

Related tools

Text Formatter

Convert text to bold, italic and Unicode styles.

Open →

Word Counter

Count words, characters and reading time.

Open →

Text Diff Checker

Compare two texts side by side.

Open →

Learn more

Read our detailed guide about this tool

How does it work?

This tool uses the Web Speech API, a native browser feature that converts speech to text using your operating system's speech engine. On Windows it uses the built-in Windows Speech Recognition, on macOS it uses Siri/Dictation, and on Android/iOS it uses the device's native speech recognizer. Because the processing happens entirely on your device through the browser, no audio data is ever transmitted to our servers or any third-party cloud service. This makes it ideal for transcribing sensitive conversations, medical notes, legal dictation, or any situation where privacy is paramount.