As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/m/assemblyai-universal-3-6-pro-realtime/

# AssemblyAI Universal-3.6 Pro Realtime

AssemblyAI, Universal-3 family. Status: current. Type: speech and audio. Released: 2026-09-29.

## How to call it

| Provider | Model id | Endpoint | Docs |
|---|---|---|---|
| AssemblyAI API | `universal-3-6-pro` | wss://streaming.assemblyai.com/v3/ws?model=universal-3-6-pro | https://www.assemblyai.com/blog/universal-3-6-pro-realtime |
| AssemblyAI Voice Agent API | `(default STT)` | wss://agents.assemblyai.com/v1/ws |  |

## Pricing

- Per hour: $0.45
- Unit as published: per hour of streaming session (same as Universal-3.5 Pro Realtime); Universal-Streaming EN/multi $0.15/hr
- Source: https://www.assemblyai.com/pricing
- Last checked: 2026-09-29

## Specs

- Input: audio, text
- Output: text
- Context window: not published
- Max output: not published
- Open weights: no
- Licence: proprietary

## Where it stands

- Newer speech and audio models in the registry since its release: 13. The 5 newest:
  - NVIDIA Nemotron 3.5 Transcribe (30B-A4B) (2026-10-28) https://postcutoff.com/m/nemotron-3-5-transcribe/
  - Hy-SimulMT-30B-A3B (2026-10-22) https://postcutoff.com/m/hy-simulmt-30b-a3b/
  - Eleven Realtime v1 Max / Mini (2026-10-20) https://postcutoff.com/m/eleven-realtime-v1-max/
  - Voxtral Mini Transcribe 3 (+ Mini Transcribe Realtime 3) (2026-10-20) https://postcutoff.com/m/voxtral-mini-transcribe-3/
  - Voxtral Small Transcribe 3 (2026-10-20) https://postcutoff.com/m/voxtral-small-transcribe-3/
- Before it from AssemblyAI: AssemblyAI Universal-3.5 Pro (async) (2026-07-07) https://postcutoff.com/m/assemblyai-universal-3-5-pro/
- Closed weights; access is hosted only.

## What stands out

- Promptable streaming STT for voice agents: Prompting + keyterms together, real-time diarization, entity-aware endpointing and native code-switching in 32 languages with auto language detection; 5.13% normalized WER (vs 5.80% for 3.5 Pro Realtime), short-response WER 1.45%; median endpoint latency 537 ms. Source: https://www.assemblyai.com/blog/universal-3-6-pro-realtime

## Notes

Lineage: Universal-3 Pro Streaming (Mar 2026) -> Universal-3.5 Pro Realtime (2026-06-23) -> 3.6 (2026-09-29). Older streaming ids u3-rt-pro/u3-pro replaced. Voice Agent API ($4.50/hr all-in: STT+LLM+TTS) GA April 2026. AssemblyAI roadmap targets 30+ native languages for the next Universal-3.x in Q4 2026.

Sources: https://www.assemblyai.com/blog/universal-3-6-pro-realtime , https://www.assemblyai.com/llms/models.md , https://www.assemblyai.com/pricing

Model page: https://postcutoff.com/m/assemblyai-universal-3-6-pro-realtime/