Speech to Text — Free Online STT Voice Recognition
Transcribe speech in real-time with your microphone, or convert audio files to text using AI Whisper.
⚠️ This browser does not support the Web Speech API. Please use Chrome or Edge, or use the File Upload tab below.
Click the button to start voice recognition
0 chars
ℹ️ Microphone mode uses your browser's built-in speech recognition. Works best in Chrome and Edge.
🤖 AI Whisper — 100% Local Processing
Your audio files are never sent to a server. The AI model runs entirely in your browser.
First use: model (~75MB) is downloaded automatically and cached for future use.
First use: model (~75MB) is downloaded automatically and cached for future use.
Drop your audio file here
Supports MP3, WAV, M4A, OGG, FLAC, WEBM
Loading model...
0%
💡 Tips
- For best microphone accuracy, speak clearly in a quiet environment.
- The Whisper model is cached after the first download — subsequent uses are instant.
- For long audio files, the Base model provides more accurate results than Tiny.
Frequently Asked Questions
What is the difference between microphone and file mode?
Microphone mode uses your browser's built-in speech recognition for real-time transcription. File mode uses the AI Whisper model running entirely in your browser to transcribe audio files — 100% local and private.
Which languages are supported?
Microphone mode supports English, Korean, Japanese, and many more. File mode (Whisper) supports 99 languages including English, Korean, Japanese, Chinese, Spanish, French, and German.
Are files uploaded to a server?
No. In file mode, the AI model runs entirely in your browser. Your audio files are never sent to any server.