Transcribe a recorded call to text
Phone call to text: the dialogue of a recorded call as text with the start and the end time of every line and the two voices named.
A recorded call is one file with two voices in it. Export the recording from the phone system, upload the file, and the dialogue comes back as text with the start and the end time of every line. One file is up to 30 minutes, the free plan is $0.
How to transcribe the recording of a call
- 1
Export the recording of the call
A headset or a call system leaves a file behind when the call ends. Take that file, with both sides of the conversation in it, and keep the original instead of the excerpt that the mail sends.
- 2
Send the file and split the voices
The file is up to 30 minutes. Put it on the widget above, set the language or leave it on the automatic detection, and switch on the split by speaker: the agent and the client arrive as two separate voices.
- 3
Read the lines that matter
Every line carries the time it starts and ends. Export the text and find the order number by a word in it, and correct a name written wrong in the editor of the app.
- 4
Put the text into the ticket
Export as TXT or Markdown for the description of a ticket, as CSV for a sheet of calls, and as DOCX on Pro for a handover. The file is named after the recording, so the ticket and the file keep the same name.
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 the transcript of a call contains
- One recording of a call
up to 30 minutes on the free plan, no minute limit on Pro
- The two voices of the call
each voice gets a label of its own when the split by speaker is on
- The file of the call
the recording of the headset or of the call system, with both sides in it
- Your audio
never used to train models for other customers, never sold
Why the recording is not the summary
The call ends and the recording stays in the mailbox of the phone or in the folder of the system. Then comes the typing: a summary for the ticket, the order number, the address of the customer, the name of the second person. All of it is in the audio, and none of it can be found there.
Tips
Put the date and the client into the name of the file.
Turn on the split by speaker for every call with two voices.
Export CSV when the calls have to go into a spreadsheet.
Questions this page answers
Can the agent and the customer be told apart?
Yes, turn on the split by speaker before you send the file. The two voices are then labelled, and the transcript reads as a dialogue instead of a paragraph that nobody can follow.
What if the recording sits in two files?
Upload them one after the other. Every file keeps its own timecodes, so the order of the parts is what tells the story; write the part number into the name of the file.
What happens to the audio afterwards?
The audio and the transcript stay in your account until you delete them in the app, and on the Free plan the transcript is kept for 7 days. A word is corrected in the editor, and the corrected text stays in the transcript. The audio is never sold.
Do I need a card to try it?
No. The free plan is $0 with 3 files a day and up to 30 minutes per file. Pro costs $10 a month paid yearly or $20 a month paid monthly.
Reading: 6 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.