Speech-to-Text guide

Plan realtime and asynchronous transcription requests, language hints, speakers and timestamps.

Create a Preview key ↗Read the docs

Interface preview

Start with a sample.
Inspect every field.

The Preview returns simulated data and never implies that customer audio was processed.

curl https://api.audelyr.ai/v1/preview/transcriptions \
+  -H "Authorization: Bearer $AUDELYR_PREVIEW_KEY" \
+  -H "Content-Type: application/json" \
+  -d '{"sample_id":"multilingual-support-call"}'

Overview

Plan realtime and asynchronous transcription requests, language hints, speakers and timestamps.

Before you begin

Create and verify an Early Access account, then generate a Preview API key from the console. Keys are displayed once.

Request lifecycle

Every response includes a request identifier. Asynchronous resources expose stable states and errors use a predictable envelope.

queued
processing
completed
failed

Production note

The Preview accepts only built-in sample identifiers. Audio URLs and uploaded files are rejected until real inference is available.

Early Access

Build the interface
before the infrastructure.

Explore the honest Preview, then tell us what production voice needs from Audelyr.

Create an account Contact sales