{"repo":"NousResearch/hermes-agent","public_id":"13881","display_label":"Audio passthrough and STT control for voice input","summary":"These requests relate to sending audio directly to models that support it natively, rather than converting voice to text first. One request also asks for an option to disable automatic speech-to-text processing for voice messages.","subsystem":"gateway","counts":{"members":3,"open_issues":2,"open_issues_distinct":2,"open_prs":0,"closed_issues":1,"merged_prs":0,"attempt_prs":0},"landed_fix":null,"resolution":{"state":"unresolved","by":null},"freshness":{"state":"never_verified","last_verified_at":null,"is_stale":false},"grouping":{"backbone":"LLM_ONLY","link_density":0.36000000000000004},"fix_edges":[],"members":[{"kind":"issue","number":13881,"title":"[Feature]: Send audio directly to model (Gemma 4)","url":null,"state":"open"},{"kind":"issue","number":15145,"title":"[Feature]: Option to disable automatic speech-to-text for voice messages","url":null,"state":"closed"},{"kind":"issue","number":40873,"title":"[Feature]: Open-AI compatible api audio passthrough using voice chat for models that have built in support for audio.","url":null,"state":"open"}],"trust":{"default_tier":"verified","includes_suggested":false}}