Speech to Text
Transcribe audio or your voice into accurate text.
Audio is processed on our server and not stored. Best with clips under ~10 minutes.
About Speech to Text
Record straight from your microphone or upload an audio file, and we transcribe it into clean, accurate text using OpenAI's Whisper model. It auto-detects the language (or pick one), and you can copy the transcript, download it, or send it to the editor to turn back into speech.
- 1Record your voice or upload an audio file.
- 2Pick a language or leave it on auto-detect.
- 3Get your transcript — copy, download, or send to the editor.
FAQ
What languages are supported?
Whisper handles 90+ languages and detects the spoken language automatically. You can also set it manually for best accuracy.
Is my audio stored?
No — your audio is processed on our server to create the transcript and is not saved.
How long can the audio be?
Clips up to roughly 10 minutes work best. For longer recordings, split them into parts.
Which file types work?
Most common audio and video files (mp3, wav, m4a, webm, ogg, mp4, and more).