Short answer: The docs don’t specify a preferred or fixed whitelist for v3-alpha audio tags, and neither [disgust] nor [disgusted] is called out. v3-alpha treats audio tags as free-form, “non-exhaustive” cues—you can use similar, contextually appropriate tags—but effectiveness varies by voice, so there’s no guarantee the two will perform identically. The guidance is to experiment and pick what works best for your voice. (elevenlabs.io)
Relevant passages:
“Audio Tags (Non-Exhaustive)… You can infer similar, contextually appropriate audio tags,” and “There are likely many more effective tags beyond this list. Experiment.” (elevenlabs.io)
“The voice you choose and its training samples will affect tag effectiveness. Some tags work well with certain voices while others may not.” (elevenlabs.io)
Blog overview confirming tags are open-ended (“can be anything from [excited]… to [explosion]”). (elevenlabs.io)
Help Center summary of v3-alpha audio tags (emotions, delivery, non‑verbal) without a fixed list. (help.elevenlabs.io)
solid pulsar
random oak