Transcribe voice memos to text
A voice memo is a small audio file, and small files are exactly what a transcript service is for: upload it and you get the text with a timestamp per line, ready to paste into a message, a task or a note. The limit is 64 MB and 120 minutes per file, the free plan is $0 with 3 files a day, and Pro is $10 a month when you pay yearly.
What a memo costs you
Minutes of audio are the unit on every plan, so a memo is counted by its length. The shares below are calculated from the 1,500-minute Pro allowance.
| Memo | Minutes counted | On the free plan | On Pro (1,500 minutes a month) |
|---|---|---|---|
| 30 seconds | 0.5 | 1 of 3 files a day | 0.03% of the allowance (calculated) |
| 3 minutes | 3 | 1 of 3 files a day | 0.2% of the allowance (calculated) |
| 15 minutes | 15 | 1 of 3 files a day | 1% of the allowance (calculated) |
| 30 minutes | 30 | the last file the free plan accepts | 2% of the allowance (calculated) |
How to get the memo out of your phone
| Device | How the file is exported | What to do with it |
|---|---|---|
| iPhone (Voice Memos) | share the recording and save it to Files or send it to yourself | upload the file in the app |
| Android (Recorder) | save the recording, or share it to your drive or messenger | upload the file in the app |
| Desktop recorder | the audio file the recorder wrote | upload the file in the app |
| Claude or ChatGPT | attach the memo to the conversation | the plugin sends it to the same API and returns the text |
Dictation, not recording
The same text goes through the same pipeline either way. If you dictate into a notes app, export that file as audio and upload it — the result is the same transcript with the same timecodes.
Memos inside an assistant
There is a plugin for Claude and one for ChatGPT, and an MCP server behind them. Attach a voice memo to the conversation, ask for a transcript, and the file goes to the same API — with a summary and the action items, if you ask for them.
Put a file on the page and read the first lines.
The widget below is the same one as on the home page: file → transcript with timecodes and speakers → export. The transcript is saved to your account.
Drop an audio or video file
or — mp3, wav, m4a, mp4, up to 64 MB and two hours
Transcription runs under your account: sign in or create a free account.
No account yet? The free plan needs no card. Create a free account or sign in.
Questions this page answers.
How long can a voice memo be?
Up to 120 minutes and 64 MB per file — and up to 30 minutes on the free plan, which refuses a longer file with a clear error.
Do you keep my voice memos?
The audio and the transcript stay in your account until you delete them; on the free plan transcripts are kept for 7 days. Deleting a transcript removes the file with it, and the deleted file is gone from the live system immediately and from encrypted backups within 30 days.
Can I dictate instead of recording?
Yes. A dictation is just an audio file, so it goes through the same pipeline and comes back with the same timecodes.
Is there a mobile app?
No. The service is a web app, a REST API, an MCP server and the plugins for Claude and ChatGPT. That is the whole list.
Can I transcribe several memos at once?
One file per job in the interface; a script can loop over the API — the endpoint is the same for a single memo and for a hundred.
Related pages.
The general guide.
Transcribe Russian audio to text
Memos in Russian, and in the Russian-English mix.
The long version of the same workflow.
Plans and limits.
Mark Burmistrov, Founder.
Every number on this page comes from the service contract, the pricing page or our own measurements. The author of the page and the publisher of the site are the same person. Questions and corrections: support@transcrib.si.