Loading the listening set...
Research listening preview for multilingual zero-shot text-to-speech.
This page presents outputs from the current Audio8-TTS-0.6B preview checkpoint. It includes the recommended language set, targeted pronunciation challenges, tongue twisters, complete classical Chinese works, cross-lingual cloning, and dense lexical tests.
The listening set combines difficult in-the-wild speech with cleaner expressive prompts. This mix separates robustness to imperfect recordings from pronunciation, prosody, and cross-language speaker-identity transfer.
Loading the listening set...