aiqbench takeAI Products

Gradium AI has updated its default text-to-speech model to prioritize hard-case accuracy in voice agents, achieving an 81.0% pass rate on complex data fields like order numbers and emails while reducing latency to 216 ms. This shift addresses a critical bottleneck where previous models failed precisely on the information users needed most during automated interactions. The company has also open-sourced its rigorous evaluation dataset to foster transparency in benchmarking TTS performance against competitors.

Source coveringMarkTechPost

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

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

MarkTechPostSeptember 1, 20263 min read

Speed and accuracy usually pull against each other in text-to-speech. Gradium AI's new default model reports both: an 81.0% human-rated pass rate on 500 hard sentences across five languages, at 216 ms P50 time-to-first-audio on Coval. The evaluation set is open on Hugging Face under CC BY 4.0. The post Gradium AI Releases New Default TTS Model: 81.0% Hard-Case Pass Rate at 216 ms Time-to-First-Audio appeared first on MarkTechPost.

Voice agents fail on exactly the parts of a call that matter most: the order number, the callback digits, the email address the caller has to write down. Gradium AI has released a new text-to-speech model and made it the default across its API and Studio. The company reports an 81.0% human-rated pass rate on a 500-sentence…

Excerpt shown under the publisher's RSS terms · 57 words · full text and figures are on the publisher's site

Read at MarkTechPost ↗Ask about this article