Does the service listen to calls live?
No. It reads a file that already exists. There is no call to connect, no number to give and no microphone to open: the recording is uploaded as a file.
Phone call to text
Transcribe a phone call to text
Transcribe a phone call to text: upload the recording of the call and get a transcript with a timecode on every line and the speakers named.
3 files a day up to 30 minutes, free99+ languagesSpeaker separation and timestamps
In short
Record the call, upload the file, and the transcript comes back with a timecode on every line and the speakers named on request. One file is up to 30 minutes; the free plan is $0 with 3 files a day.
How to transcribe a phone call
- 1
Keep the recording of the call
Whatever the phone or the headset produced is the file to upload. It may be up to 30 minutes at most, and both sides of the call are in it.
- 2
Upload it and split the voices
Drop the file on the widget above. Set the language or leave it on automatic detection, and switch on the speaker split so the two voices do not end up in one column.
- 3
Find the sentence you need
Every line carries the time it starts and ends, so the moment with the number or the name is one search away. Export to TXT, Markdown, SRT, VTT, CSV or DOCX.
What you get
- TXT
Plain text for an email, a note or a chat
- SRT
Subtitles for video editors and platforms
- VTT
Subtitles for a browser and a website
- CSV
A table: time, speaker, text
- DOCX
A Word document with speakers and times
- Markdown
Text with headings for notes
What a call transcript contains
| What | Value |
|---|---|
| One file | up to 30 minutes on the free plan, no minute limit on Pro |
| Price | $0: 3 files a day. Pro is $10 a month paid yearly ($120 a year) |
The case
Why the recording is the only copy
A phone call leaves one artefact: a recording. It sits in the voice memo of the phone, it does not get a summary, and a month later nobody can find the part where the number was given. Turning it into text takes one upload and makes the call searchable, quotable and readable at a glance.
Tips
Write the date into the file name; calls repeat themselves.
Split the speakers as soon as the file is chosen.
Export CSV when the call has to go into a sheet.
Questions this page answers
Can two people be told apart?
Yes, switch on the split by speaker. The transcript then names the speakers, which is the difference between a call you can read and a paragraph without a voice.
Is the call kept after the transcript is made?
The transcript is saved in your account so you can fix a word and export it again. A Russian or mixed file is processed by our own engine outside the United States, and the audio is never used to train models for other customers.
What does it cost?
The free plan is $0 with 3 files a day and up to 30 minutes per file, no card. Pro is $10 a month when you pay yearly, or $20 a month when you pay monthly.
Reading: 5 minutesUpdated 
Transcribsi editorial team
Drop a recording — the text arrives in a minute
Speakers by name, a time on every line, export to TXT, SRT, VTT, CSV and Markdown.
3 files a day up to 30 minutes, free99+ languagesSpeaker separation and timestamps