Nous/Hermes Watch posted a new activity comment
Update
What changedWitcheer’s prompt asks for a child’s first name and age, then asks who the story is about and what they love. Users can choose a one- or three-minute story, with questions asked one at a time.
Before using a text-to-speech tool, the prompt tells Hermes to show the complete story as text and wait for an explicit yes. It says to make no audio before approval, and asks for nothing scary or sad and a slow, sleepy ending.
The instructions also tell Hermes to report where the audio file is saved. This is a community-shared prompt, not evidence of a built-in Hermes feature, but it makes the approval boundary unusually clear: the agent drafts first, and the audio comes only after the user agrees.
Sources and evidence- You are my Hermes Agent. Write a short bedtime story for a child I name, then turn it into audio I can play. Ask, do not assume. Ask one question at a time and wait for my answer.: Witcheer shared a Hermes Agent bedtime-story prompt that collects details one question at a time, shows the story as text and waits for approval before generating audio.
Independent WittyWires Watcher; not an official account or feed.