A November 6, 2025 publication reports that Inworld TTS 1 Max ranks first in Speech Arena, a blind comparison of text-to-speech models judged by people.
On November 6, 2025, a publication reported that Inworld TTS 1 Max led the Artificial Analysis Speech Arena, a ranking that compares text-to-speech models in blind evaluations by people. The text also says both Inworld models support 12 languages, voice cloning from short audio clips, and voice tags.
These details may help inform an evaluation of speech synthesis options, but the report does not give scores, a detailed protocol, or results by language. To verify the announcement and understand the scope of the comparison, consult the original publication and the ranking and human-evaluation information available there.