Intel / post

AssemblyAI Universal-3.6 Pro arrives on OpenRouter via Sync API

Source: x.com
Date: Published Oct 15, 2026

Universal-3.6 Pro is now on @OpenRouter, served through our Sync API. One request in, one finished transcript back. No job to poll, no webhook, no WebSocket. Already running your LLM calls through OpenRouter? Your Speech-to-Text can go on the same key. https://t.co/P7vpujjZzv

Oct 15, 2026 View on X

Context

AssemblyAI has put its Universal-3.6 Pro speech-to-text model on OpenRouter, and the point of its announcement is the shape of the call rather than the model (AssemblyAI post). It is served through AssemblyAI's Sync API: an application sends the audio in one request and gets the finished transcript back in the response. The company contrasts that with the usual alternatives it names, where transcription is a job the developer submits and then either checks repeatedly until it is done (polling), waits for a callback to their own server (a webhook), or receives piece by piece over an open connection (a WebSocket). AssemblyAI presents the synchronous call as removing that extra machinery.

The second half of the pitch is consolidation: teams already sending their language-model requests through OpenRouter can run transcription on the same API key rather than a separate account and credential. The post itself gives no pricing, latency or accuracy figures; OpenRouter's own announcement of the listing, which states pricing and comparisons with the previous Universal-3.5 Pro model, is covered separately.

Terms in this piece · Glossary

streaming — Sending a model's response token by token as it is generated, so the reader sees text immediately instead of waiting for the whole answer.

Read the source x.com