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 universal-3-6-pro.

Available models

Name	Parameter	Description	Best for
Universal-3.6 Pro Streaming Recommended	`"universal-3-6-pro"`	Our flagship streaming model. 32 languages with native code-switching, plus prompting and conversational context features.	Real-time voice agents needing the latest accuracy, broad language support, and conversational context.
Universal-3.5 Pro Streaming	`"universal-3-5-pro"`	The previous flagship streaming model. Still fully supported, with the same features as Universal-3.6 Pro but 19 languages instead of 32.	Existing integrations pinned to this model.
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-3.6 Pro / 3.5 Pro Streaming Recommended	Universal-Streaming English	Universal-Streaming Multilingual
Latency	Fastest	Fast	Fast
Supported languages	32 on Universal-3.6 Pro, 19 on Universal-3.5 Pro (full list)	EN	EN, ES, DE, FR, PT, IT
Partial transcripts	Yes	Yes	Yes
Multilingual	Native Code Switching	No	Per Turn
Entity accuracy	Best	Okay	Okay
Disfluencies & filler words	Yes	No	No
Language detection	Yes	No	Yes
Non-speech tags	No	No	No
Customization	Keyterms prompting (known context) + Native prompting (unknown context)	Keyterms prompting (known context)	Keyterms prompting (known context)

For detailed setup and configuration of Universal-3.6 Pro Streaming, see the Universal-3.6 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-3-6-pro",  # universal-3-5-pro | universal-streaming-english | universal-streaming-multilingual
}

client.connect(
    RealTimeParameters(
        sample_rate=16000,
        speech_model="universal-3-6-pro",  # universal-3-5-pro | universal-streaming-english | universal-streaming-multilingual
    )
)

const CONNECTION_PARAMS = {
  sample_rate: 16000,
  speech_model: "universal-3-6-pro", // universal-3-5-pro | universal-streaming-english | universal-streaming-multilingual
};

const transcriber = client.streaming.transcriber({
  sampleRate: 16_000,
  speechModel: "universal-3-6-pro", // universal-3-5-pro | universal-streaming-english | universal-streaming-multilingual
});