AssemblyAIReleased on Jan 1, 2024

Universal Streaming: Benchmarks, Pricing & Context Window

Universal Streaming is a speech-to-text model from AssemblyAI, released in January 2024.

Universal streaming speech recognition model

Input
Audio
Output
Text

Universal Streaming API

POST/v1/stt/transcribe

Any audio format up to 25 MB.

Missing Audio file

Run a request to see the response

Use it in your code

OpenAI-compatible endpoint through the LLM Stats gateway.

import requests

with open("audio.mp3", "rb") as f:
    response = requests.post(
        "https://gateway.llm-stats.com/v1/stt/transcribe",
        headers={"Authorization": "Bearer YOUR_API_KEY"},
        files={"file": f},
        data={"model_id": "universal-streaming"},
    )

print(response.json()["text"])

Need an API key? Create one above in the playground, or read the API documentation.

Universal Streaming license

Universal Streaming is released under the Proprietary license, which restricts commercial use.

License
Proprietary
Non-commercial

Proprietary license - usage restrictions apply

FAQ

Common questions about Universal Streaming.

Who created Universal Streaming?

Universal Streaming was created by AssemblyAI.

What is the license for Universal Streaming?

Universal Streaming is released under the Proprietary license.

Is Universal Streaming multimodal?

Yes, Universal Streaming is a multimodal model that can process both text and images as input.