Audio · DSS / WAV / MP3
Dictaphone recordings to text
Professional dictation hardware from Olympus, Philips, and Sony writes DSS, DS2, WAV, or MP3.
Worth knowing: DSS is heavily compressed for speech. It transcribes fine, but a WAV setting will always do better.
What you get back
transcript.txt
[00:14] Maya Revenue grew fifteen percent,
and the retention metrics are green.
[00:31] Daniel Good. What are we committing to for Q2?
[00:38] Priya Concrete steps by Friday.Speakers separated and labelled — rename once and it flows through every export.
Clean text
Punctuated and paragraphed, not a raw stream of words.
Dialogue by speaker
Each voice labelled and separated, up to 6 speakers.
Subtitles
SRT, VTT, and ASS, or burned into the video without a watermark.
AI summary
Decisions, action items, and who owns them.
FAQ
Dictaphone recordings questions
Specific to Dictaphone recordings: size limits, what affects accuracy, and what you can export.
How do I convert Dictaphone recordings to text?
Upload the file and the engine handles the rest — language detection, transcription, punctuation, speaker separation, and timecodes. Nothing to configure, and no conversion to another format first.
Is there a file size limit for Dictaphone recordings?
30 MB on the free plan, up to 5 GB on paid plans. For video we extract the audio track first, so a large file costs the same minutes as its audio would.
How accurate will it be?
Around 99% on clear recordings. DSS is heavily compressed for speech. It transcribes fine, but a WAV setting will always do better.
What can I export?
Plain text, a dialogue split by speaker, Word, PDF, subtitles as SRT, VTT, or ASS, and an AI summary with decisions and action items.
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.