Product
Audio transcription
Turn any recording into clean, punctuated text with speakers separated and timecodes on every word.
Upload an audio file in any common format and get back text you can actually read — punctuated, split into paragraphs, and attributed to whoever was speaking. There is nothing to configure: the language is detected automatically across 99 options, including recordings that switch language partway through.
The output is not a single blob. You get plain text for reading, a dialogue view split by speaker for meetings and interviews, word-level timecodes for anything you need to verify against the audio, and an AI summary when you just want the decisions.
00:14MayaRevenue grew fifteen percent this quarter.
00:31DanielWhat are we committing to for Q2?
Any format, no conversion
MP3, WAV, M4A, AAC, FLAC, OGG, Opus, WMA, AMR, and more. Upload what your recorder produced.
Files up to 5 GB
Long recordings stay in one piece instead of being split into chunks you have to stitch back together.
Word-level timecodes
Every word carries a timestamp, so a quote can always be traced back to the second it was said.
Punctuation and paragraphs
The transcript reads like written text, not a stream of lowercase words.
Questions
What people ask about audio transcription before they rely on it.
Which audio format gives the best accuracy?
WAV or FLAC — nothing has been discarded by compression. In practice anything from 128 kbps MP3 upward transcribes about as well; the microphone matters far more than the format.
How long can a single file be?
Up to 5 GB, which is several hours of audio. Long files stay in one piece rather than being split into chunks you have to stitch back together.
Can I edit the transcript afterwards?
Yes, and you should for anything important. Editing keeps timecodes in sync, so corrected text still points at the right moment in the recording.
Be first in when it opens.
Sign-ups are not open yet. Leave your address and you get one email the day they are — sixty minutes free, no card.