Gradium AI Releases New Default TTS Model: 81.0% Hard-Case Pass Rate at 216 ms Time-to-First-Audio

AITopTools Editorial TeamSeptember 1, 2026

What changed

Gradium AI released a new default text-to-speech model, which turns written text into spoken audio. The company reports that it passed 81.0% of 500 difficult, human-rated sentences in five languages, with the first audio arriving in a median 216 milliseconds on Coval.

What this means for you

Voice-app developers and creators may be able to deliver faster, more natural-sounding speech with this release. The 500-sentence evaluation set is available on Hugging Face under a Creative Commons license, making the claims easier to review and reuse.

Related AI tools

Explore directory listings connected to the products, companies, and workflows in this story.

MicroStrategy AI Willy Rater AI Data Modeling Longevity Compass AI

Related AI news

New AI featuresAug 31, 2026

Google AI Releases TimesFM-3: A 330M Parameter Zero-Shot Foundation Model For Multivariate Time Series Forecasting

Researchers and organizations can access the model’s weights for testing multivariate forecasts, but the license does not allow commercial or production use. That limits immediate use in business products.

MarkTechPostSee why it matters

AI toolsAug 31, 2026

Instagram puts new limits on undisclosed AI profiles

People running undisclosed AI profiles may find it harder to reach Instagram users. The change is already being applied on Instagram, although the feed does not specify the exact limits.

TechCrunch AISee why it matters

AI toolsAug 31, 2026

Instagram admits users often can't tell AI profiles from real people

AI profile operators may need to use the new label to avoid reduced visibility, while users get a clearer signal that an account is not run by a real person. The change reflects Instagram’s effort to distinguish AI-generated accounts from human users.

The DecoderSee why it matters