Voice and music · by pyannoteAI

pyannoteAI

Label who spoke when, and recognize known speakers by voice.

speech, link → data, series · speech → events · speech → data
Way in
Official APISign up yourself, api key
To start
$30-day free trial, no card; Developer €19/mo and Starter €99/mo each include equal usage credit
Runs
In the cloud
Checked
Nov 4, 2026Prices as of that day

What it can do 4

Diarize an audio file (Precision-3 or Community-1)speech, link → data, seriesPrecision-3 €0.112/h (Developer) or €0.096/h (Starter); Community-1 €0.035/h
Diarize a live stream (Live-1)speech → eventsLive-1 €0.198/h (Developer) or €0.170/h (Starter)
Identify known speakers from voiceprintsspeech → data€0.015 per voiceprint created; per-hour identification rate not printed
Orchestrate STT + diarization into a speaker-labelled transcriptspeech → text, data€0.168/h (Developer) or €0.144/h (Starter)
Prices and limits as of Nov 4, 2026, from pyannoteAI’s own pages. They change; check before you rely on them.Not affiliated with pyannoteAI. Not advice.Something wrong?
Made by Jasper Burns

A short note when I ship something new, about once a month. One list for all my projects.