Conference Call Transcription: Audio to Text With Speakers
Upload conference calls recordings and get every word, who said it and when
No account? The first 30 minutes of any file are free. Create a free account for premium on your first file.
Rated 4.8 out of 5 from 1,646 customer ratings
Upload the recording, leave the language on Auto-detect, and the transcript comes back with timestamps and speaker labels. On 20 November 2026 a 75-second WAV test file was ready in 10 seconds with 22 in 100 words different from the human transcript. The first 30 minutes are free with no signup.
Why transcribe conference calls here
Who said what
Each speaker gets a label you can rename once for the whole file.
Timestamps on every line
Jump to any moment of the audio from the transcript.
Every common format
MP3, M4A, WAV, OGG, OPUS, CAF, FLAC, AAC and video files upload as they are.
Measured, not promised
Tested live on a WAV file; the lines it returned are on this page.
How it works
Upload the file
Drop the audio or video file here, or paste a link to it.
Get the transcript
Every word with timestamps and speaker labels, usually in under a minute for short files.
Download or share
TXT, DOCX, PDF, SRT or VTT, or a share link.
Conference calls to text: a short guide
Tested live on this page
On 20 November 2026 we uploaded four people talking in an English meeting through this tool as a WAV file at phone-line quality, with the language left on Auto-detect.
| What | Result |
|---|---|
| File | WAV, PCM 16-bit, 8 kHz, mono |
| Length | 75 s |
| Transcript ready in | 10 s |
| Words different from the human transcript | 22 in 100 (159 words) |
| Language found by Auto-detect | English |
| Speakers found | 3 |
The lines it returned
The recording is a 75-second excerpt of a real meeting from the AMI Meeting Corpus, released under the Creative Commons Attribution 4.0 licence. It is scored against its human transcript, leaving out filler words such as um and uh. People talking over each other is the hardest case for any transcript. The transcript is ours, not edited by hand.
| Time | Speaker | Text |
|---|---|---|
| 00:06 | Speaker 1 | I am the small, cute, and furry. When Planet of the Apes becomes real, I am going to be up there with them. |
| 00:26 | Speaker 2 | You can take as long over this as you like because we haven't got an awful lot to discuss. Oh, we do, we do. Don't feel like you're in a rush anyway. |
| 00:36 | Speaker 1 | I could have told you a whole lot more about Beagle. |
| 00:38 | Speaker 2 | Okay, cool. We might have to get you up again then. I don't know what mine is. I'm going to have to think on the spot now. |
Tips for conference calls
- Upload the recording from your conferencing or phone system. Several speakers are told apart and labelled, and you can rename each label once for the whole file.
- Phone-line sound is the hardest case: ask people to use a headset and not to talk over each other, and check names and numbers against the audio.
What it costs
The first 30 minutes of a file are transcribed free with no signup. With a free account, TXT, DOCX, PDF, SRT and VTT downloads and speaker labels are free. Paid plans and the Weekly Pass take longer files, up to 10 GB.
More audio to text
Audiobooks transcriptionConference talks transcriptionOnline course lessons transcriptionRadio broadcasts transcriptionCoaching sessions transcriptionCustomer support calls transcriptionSales calls transcriptionJob interviews transcriptionFocus groups transcriptionOral history interviews transcriptionEarnings calls transcriptionUser research interviews transcriptionLanguage lessons transcriptionReal estate calls transcriptionTutorials transcription
Frequently asked questions
The first 30 minutes of a file are transcribed free with no signup. With a free account, TXT, DOCX, PDF, SRT and VTT downloads are free.
On our WAV test file, 22 in 100 words differed from the human transcript. Noisy rooms, people talking over each other and far-away microphones lower that, so check names and numbers.
No. WAV files with PCM 16-bit sound upload as they are, like MP3, M4A, WAV, OGG, OPUS, CAF, FLAC, AAC and most video files.
Auto-detect picks the spoken language for you; you can also set it before uploading. Dozens of languages are supported.
Related tools
Transcribe Audio
Upload a recording and our AI audio transcriber returns a timestamped transcript, usually in under a minute
Speaker Identification
Upload a conversation and get a transcript split by speaker, with a timestamp on every turn
Audio to Word
Transcribe audio and download it as an editable DOCX file