Upload a recording — a meeting, an interview, a lecture, a voice note — and get back a clean transcript split by speaker, which you can export as Word, PDF, plain text, subtitles or a spreadsheet.
It is built for real conversations, including Arabic, English and the mix of the two that is common in the region, and it labels speakers rather than returning one undivided block of text.
Transcription runs on a secure cloud function because speech recognition is too heavy for a phone browser; the audio is processed and not stored, and nothing else on the site leaves your device.
How to use it
Upload a recording, or paste a link to one.
Choose the language — English, Arabic, or a conversation that mixes both.
Wait while it is transcribed and split by speaker.
Export as Word, PDF, plain text, subtitles or a spreadsheet with timings.
Supported formats and limits
Input
MP3, WAV, M4A, MP4 and other audio and video
Output
Word, PDF, TXT, subtitles, or a spreadsheet
Languages
Arabic including Levantine dialects, English, and mixed
Speakers
Labelled separately rather than one block of text
Where it runs
A secure cloud function; the audio is not stored afterwards
Not for: Perfect accuracy on poor recordings — heavy background noise and people talking over each other still cause mistakes.
Frequently asked questions
What languages are supported?
Arabic — including Jordanian and Levantine dialects — English, and conversations that switch between the two mid-sentence. The transcript keeps each part in the language it was spoken in.
Can I get subtitles or a spreadsheet?
Yes. The finished transcript exports to Word, PDF, plain text, subtitle files, and a spreadsheet with timings — pick whichever the next step needs.
Is my recording stored?
No. The audio is transcribed and not kept. A transcript is only saved if you choose to save it to your own library while signed in.