Aura-1, Explained Simply
What Aura-1 is, what it does well, and what it costs — released 2024-04-11 by Deepgram.
- Aura-1 is an AI tool by Deepgram that turns written text into spoken audio.
- It recently got an update to fix annoying volume issues.
- Now, every AI voice stays at a steady, predictable loudness level.
Want a heads-up when Deepgram updates?
We email you the moment a new Deepgram version drops — plus plain-English release notes like these. No spam.
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Aura-1 is a text-to-speech (TTS) model made by a company called Deepgram. It is designed for app developers, video creators, or anyone who wants to generate realistic human-sounding voices from written words without needing to hire real voice actors.
What it does well
Its biggest strength right now is keeping the audio volume perfectly steady. When you use AI to generate voices, different voices can sometimes end up louder or quieter than each other. Even clips generated from the exact same voice might vary in volume. Aura-1 fixes this by making sure the loudness is consistent across all its different voices, and across every single audio clip it generates from one voice.
Worth knowing
The main thing to know is that this is an update to an existing model, specifically focused on volume control. If you are looking to use it, you will need to check out Deepgram's official voices and getting started guide to see exactly which voices are available and how to access them.
This is our plain-language summary. Read the complete, official notes on the Deepgram official changelog ↗.
Google Calendar