mirror of
https://github.com/mudler/LocalAI.git
synced 2026-10-28 09:08:54 -04:00
feat(realtime): announce speakers in transcription-only sessions With voice_recognition.identity.announce on, a realtime session sends a conversation.item.speaker event for each user turn. Only generateResponse sent this event. A transcription-only session never calls generateResponse, so it resolved the speaker of each turn and then dropped the result. In a transcription-only session with announce on, send the event before the completed transcription event of the turn, with the same item_id. The rules are the same as on the response path: no event for an unknown speaker unless announce_unknown is set, and no event for a speaker that an enforcing gate rejects. Sessions with announce off and response sessions do not change. Signed-off-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Ettore Di Giacinto <mudler@localai.io> Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>