Model selection - AssemblyAI

The speech_model connection parameter lets you specify which model to use for streaming transcription. It’s optional; if omitted, the session defaults to u3-rt-pro.

Available models

Name	Parameter	Description	Best for
Universal-3-5 Pro Streaming Recommended	`"universal-3-5-pro"`	The next generation of our flagship streaming model. More languages, improved prompting, and enhanced conversational context features.	Real-time voice agents needing the latest accuracy, broad language support, and conversational context.
Universal-3 Pro Streaming	`"u3-rt-pro"`	The most accurate model with the fastest word emissions for voice agents that demand the highest quality. Best-in-class accuracy with advanced prompting capabilities.	Real-time voice agents needing premium accuracy, elite entity accuracy, IVR replacement, agent assist, multilingual code-switching
Universal-Streaming English	`"universal-streaming-english"`	An English transcription model offering a good balance of speed and cost-effectiveness.	Cost-effective English real-time transcription, English-only real-time apps
Universal-Streaming Multilingual	`"universal-streaming-multilingual"`	A multilingual transcription model offering a good balance of speed and cost-effectiveness.	Cost-effective multilingual streaming across EN/ES/DE/FR/PT/IT

Choosing a model

Feature	Universal-3-5 Pro Streaming Recommended	Universal-3 Pro Streaming	Universal-Streaming English	Universal-Streaming Multilingual
Latency	Fastest	Fast	Fast	Fast
Supported languages	EN, ES, DE, FR, PT, IT, TR, NL, SV, NO, DA, FI, HI, VI, AR, HE, JA, ZH	EN, ES, DE, FR, PT, IT	EN	EN, ES, DE, FR, PT, IT
Partial transcripts	Yes	Yes	Yes	Yes
Multilingual	Native Code Switching	Native Code Switching	No	Per Turn
Entity accuracy	Best	Best	Okay	Okay
Disfluencies & filler words	Yes	Yes	No	No
Language detection	Yes	Yes	No	Yes
Non-speech tags	No	No	No	No
Customization	Keyterms prompting (known context) + Native prompting (unknown context)	Keyterms prompting (known context) + Native prompting (unknown context)	Keyterms prompting (known context)	Keyterms prompting (known context)

For detailed setup and configuration of Universal-3 Pro streaming, see the Universal-3 Pro Streaming page. For prompting guidance, see the Prompting guide.

Set the model

Set the speech_model connection parameter when you open the WebSocket.

Python
Python SDK
Javascript
JavaScript SDK

CONNECTION_PARAMS = {
    "sample_rate": 16000,
    "speech_model": "universal-3-5-pro",  # universal-streaming-english | universal-streaming-multilingual
}

client.connect(
    StreamingParameters(
        sample_rate=16000,
        speech_model="universal-3-5-pro",  # universal-streaming-english | universal-streaming-multilingual
    )
)

const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "universal-3-5-pro", // universal-streaming-english | universal-streaming-multilingual
};

const transcriber = client.streaming.transcriber({
  sampleRate: 16_000,
  speechModel: "universal-3-5-pro", // universal-streaming-english | universal-streaming-multilingual
});

​Available models

​Choosing a model

​Set the model

Available models

Choosing a model

Set the model