AssemblyAI: Universal-3.5 Pro Realtime

Name: Universal-3.5 Pro Realtime
Author: AssemblyAI

assemblyai/universal-3-5-pro-realtime

active stt 1 provider

Playground

AssemblyAI's most accurate realtime model (u3-rt-pro) with keyterm prompting, disfluency control, code-switching and realtime diarization.

AuthorAssemblyAI

Languagesmultilingual

Statusactive

Quick start

Universal-3.5 Pro Realtime

Create an API key

Create API key

Make a request

Pick an SDK, request mode, and language. The model and provider route are already filled in.

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "assemblyai/universal-3-5-pro-realtime",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "assemblyai"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.

Pass provider parameters

Pass provider preferences through the compatible SDK request options when you want to pin a route to a provider.

{
  queryParams: {
    provider: {
      only: ["assemblyai"]
    }
  }
}

Providers

Different providers can host the same model. Choose one provider when you need a fixed backend, or let routing select among them.

ProviderSlugPer hourLatencyiModesUptime

AssemblyAI 12 params

assemblyai

$0.45

—

Streaming

AssemblyAI

12 documented provider parameters for this route.

Pricing

ModeLanguagePer hour

Streaming Any $0.45

+ Speaker Diarization (Streaming) Any $0.12

+ Medical Mode Any $0.15

Parameters

domain body · unknown · optional

Mapped from allmodels parameter "domain".

encoding body · unknown · optional

Mapped from allmodels parameter "response_format".

inactivity_timeout body · unknown · optional

Mapped from allmodels parameter "inactivity_timeout".

keyterms_prompt body · unknown · optional

Mapped from allmodels parameter "keyterms_prompt".

max_speakers body · unknown · optional

Mapped from allmodels parameter "max_speakers".

max_turn_silence body · unknown · optional

Mapped from allmodels parameter "max_turn_silence".

min_turn_silence body · unknown · optional

Mapped from allmodels parameter "min_turn_silence".

prompt body · unknown · optional

Mapped from allmodels parameter "prompt".

sample_rate body · unknown · optional

Mapped from allmodels parameter "sample_rate".

speaker_labels body · unknown · optional

Mapped from allmodels parameter "diarization".

speech_model body · unknown · optional

Mapped from allmodels parameter "model".

vad_threshold body · unknown · optional

Mapped from allmodels parameter "vad_threshold".

Supported languages

No reviewed language list for this model yet.

Features

Speech to text

Transcribes spoken audio to text.

speech_to_text

Streaming

Real-time streaming transcription over WebSocket.

streaming

Multilingual transcription

Multilingual code-switching.

multilingual_transcription

Speaker diarization

Identifies and labels multiple speakers.

speaker_diarization

Word-level timestamps

Returns word-level timestamps.

word_timestamps

Code

ElevenLabs SDK streaming STT

Streams microphone or file audio through the ElevenLabs-compatible allmodels route.

import { ElevenLabsClient } from "elevenlabs";

const client = new ElevenLabsClient({
  apiKey: process.env.ALLMODELS_API_KEY,
  baseUrl: "https://api.allmodels.io/el"
});

const connection = await client.speechToText.realtime.connect({
  modelId: "assemblyai/universal-3-5-pro-realtime",
  languageCode: "en"
}, {
  queryParams: {
    provider: {
      "only": [
        "assemblyai"
      ]
    }
  }
});

// Send audio frames to connection, then handle transcript events.