Audio to Text Converter

Upload an audio or video file and get the text back. Files are forwarded to the configured speech-to-text provider and never stored.

File transcription is not switched on yet, so you cannot upload a file here for now. Transcripts from YouTube videos work today and need no file.

A converter, not a player: give it an audio file and it gives you the words. This is for when the recording has already served its purpose as sound and what you actually need is a document.

Upload the file and the transcript comes back as text you can copy or download. No editing, no playback, no library — just the conversion.

Frequently asked questions

What does the converter actually do?
It decodes the audio, sends it for speech recognition, and returns the recognised text. The audio is the input; the text is the output; nothing else is kept.
Can I convert several files at once?
One at a time. Batch conversion is not offered, largely because each file has to be recognised individually and the cost scales with total duration.
What output formats are available?
Plain text, and a timestamped variant where the provider returns timings. Subtitle formats are available on the video pages instead.
Does it work for non-speech audio?
No. Music, ambient recordings, and sound effects have no words to recognise. The page will return nothing useful for those.
Is there a size limit?
Practical limits come from upload size and provider duration caps rather than from the page itself. Very long recordings are better split into parts.