Welcome to Sonora! Your free trial is now active.

The Sonora Diarization API helps developers build more accurate speaker diarization pipelines that segment “who spoke when” with high precision. Clean diarization improves:

Speech-to-text accuracy: fewer word errors from speaker confusion.
Analytics: reliable speaker turns for insights and dashboards.
Training data: better-labeled datasets for downstream models.

Your trial at a glance

14 days

trial length

300 min

of audio included

Apr 28, 2026

trial ends

Minutes you haven’t used by April 28 expire with the trial.

Get started in 5 minutes

Your first diarization is three steps away.

Create an API key

Keys are shown once, so copy yours somewhere safe. Create a key in account settings.

Diarize your first file

Send a POST to /v1/diarize with your key as a bearer token. The response lists speaker turns with start, end, and speaker fields. The quickstart guide walks through the full request.

POST /v1/diarize
Authorization: Bearer $SONORA_API_KEY
{"audio_url": "meeting.wav", "speakers": "auto"}

Try the playground

Upload a sample file and run the same model without writing code. Open the playground.

Read the quickstart

We’re looking forward to seeing what you build!

The Sonora team