Audelyr
Contact salesStart building

Audelyr product

Preview

Speech-to-Text that follows the conversation

Streaming and asynchronous transcription interfaces designed for multilingual, real-world audio.

Try the Preview workflow ↗Read the docs
$0.006/min realtimeillustrative usage rate
<300 mstarget first result
61+illustrative languages

Capabilities

One interface.
Clear boundaries.

Designed as composable infrastructure, with Preview labels wherever production behavior is not yet available.

01

Realtime transcription

Documented, observable and designed to fit into your existing product architecture.

02

Speaker-aware tokens

Documented, observable and designed to fit into your existing product architecture.

03

Code-switching

Documented, observable and designed to fit into your existing product architecture.

04

Word timestamps

Documented, observable and designed to fit into your existing product architecture.

05

Async jobs

Documented, observable and designed to fit into your existing product architecture.

06

Custom vocabulary roadmap

Documented, observable and designed to fit into your existing product architecture.

Interface example

Start with a request.
Inspect every field.

Review the request shape before integrating it into your product.

const job = await audelyr.preview.transcriptions.create({
  sample_id: "multilingual-support-call"
});
console.log(job.preview, job.transcript);
01

Built for live systems

A streaming-first interface keeps application state, timing and model output in one observable session.

  • Stable event types
  • Regional processing controls
  • Usage and latency metadata
02

Formats and limits

Realtime sessions accept PCM16 or WebM/Opus. Asynchronous transcription supports AAC, AIFF, AMR, ASF, FLAC, MP3, OGG, WAV, WebM, M4A and MP4.

  • M4A via audio/mp4, audio/x-m4a or audio/m4a
  • Up to 500 MB per signed upload
  • M4A is asynchronous—not a realtime WebSocket format
03

Security by design

Keys are hashed at rest, access is scoped per account, and customer audio is not accepted by the current Preview API.

04

Frequently asked questions

The public Preview demonstrates interface shape and developer workflow. It does not perform real speech inference and is not a contractual service offer.

Early Access

Build the interface
before the infrastructure.

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

Create an accountContact sales