The AI that transcribes, tells voices apart and summarizes any conversation.
Upload the file from Meet, Zoom or your phone. An hour of recording is ready in about a minute.
See what comes out of a real meeting.
The team reviewed launch progress and pushed the release from September 1st to the 8th, because the finance integration still depends on the vendor. The 200-account target for month one stands.
Will the finance integration be ready by the 1st?
That is on the vendor. They gave me Wednesday.
If Wednesday slips, we have no time to test.
Then we move to the 8th and stop gambling on it.
Works for me. I will finish the test plan by Friday.
I will chase the vendor by Wednesday and report back.
The meeting is over. So is the work.
Tasks come out sorted, the email and the message come out written — each one pointing at the minute of the conversation it came from. You read it over, add the recipient and send.
sampleHi everyone,
In today’s meeting we decided to move the launch from September 1st to the 8th. The finance integration is on the vendor, who only answers on Wednesday, and without it there is no time to test.
The 200-account target for month one stands.
Hi all — your integration is now the blocker for the launch. The vendor gave us Wednesday. Can you confirm by then?
68×
faster than real time
measured Aug 24, 2026
9.8%
diarization error rate
vs. human-labeled ground truth
$0.10
per hour of audio
at any volume
99
languages
same pipeline, same price
Compare the full bill
Elsewhere, knowing who spoke costs extra. Here it's in the price.
The real cost of 1 hour of audio with speaker identification, at each provider's public pricing.
Public prices as of Aug 24, 2026. Groq charges $0.04 per hour but with no speaker identification at all — transparency goes both ways.
Every word in the transcript. Every voice with a name. One flat price.
How it works
Three steps, no surprises
01
Create the job
Send your audio URL or request a signed upload URL. Up to 600 MB and 4 hours per file.
POST /v1/jobs
{ "audio_url": "…",
"webhook_url": "…" }02
We process it
Async queue on GPUs. A 3-hour episode is done in minutes, not hours.
→ your webhook
{ "id": "…", "status": "done" }03
Fetch the result
JSON with speakers and timestamps, or ready-made captions. Pick the format in the URL.
GET /v1/jobs/{id}/transcript
?format=srt | vtt | txt | jsonStart free. The rest is on the way.
The Free plan is live today, with the complete summary. The larger plans open soon — what changes between them is how much audio fits.
Cancel from the app itself, no call required.
FAQ
What you'd want to know before integrating
Get started
Paste the curl, create an account, transcribe 2 hours on us.
2 free hours · no credit card · credits never expire