AI Assistant
AI Assistant listens to the selected microphone and can follow lyrics or Bible text, or respond to spoken slide commands. It runs on this computer and affects only sections or cues whose Advance mode is set to AI assistant.
Set it up before rehearsal
- Open AI Assistant in the title bar and choose Set up & test.
- Under Computer setup, use the recommended setup for this computer. Apple Silicon uses Metal; other available setups are labelled in the app when their support is experimental.
- Open Required downloads and finish every required model download.
- Under Languages, add the language used in the songs. Presenter always listens for English commands; the additional language is for following non-English lyrics.
- Use the title-bar Microphone control to choose and test the input. Restart AI Assistant after changing the device.
- In Deck Builder, select the intended section or cue and set Advance mode → AI assistant. Then choose its AI mode.
- Turn on AI Assistant and test the actual microphone, room, and service content before going live.
Turning on the engine alone does not enable automatic advancement. The deck item must also use AI assistant advance mode.
Choose the right AI mode
| Where | Mode | Use it for |
|---|---|---|
| Section | Find song and follow verses | Identify the current song, then follow its stanzas. |
| Section | Find the current song | Move to the detected song without following its stanzas. |
| Section | Follow the selected song | Follow stanzas in the song the operator has already selected. |
| Section | Listen for slide commands | Respond to spoken navigation commands. |
| Lyrics or Bible cue | Stanza tracking (follow along) | Follow stanzas or verse groups in that specific cue. |
| PDF cue | Smart Tracking (PDF pages) | Navigate PDF pages from spoken commands; it does not interpret the page's printed text. |
For either song-finding mode, Match lyrics against limits detection to songs in the section or expands it to the full lyrics database. Use the narrowest mode and matching scope that fit the service.
Operate it live
- The microphone opens only while the presentation is on an AI-enabled cue or section. Standing by or turning AI off closes capture.
- Manual navigation always wins. After an operator chooses a cue, stanza, or page, AI pauses before resuming.
- The default manual-control pause is 5 seconds. Change it from 5 to 120 seconds under Settings → AI Assistant → Manual control.
- Watch the AI status in the title bar and, when enabled, the debug information in Details. If Presenter reports that AI is falling behind, choose a lighter computer setup or recognition model.
If AI does not move the deck
Check these in order:
- The title-bar AI status says it is on and ready.
- The current section or cue uses Advance mode → AI assistant and the intended AI mode.
- The correct microphone is selected, its level moves during speech or singing, and operating-system microphone permission is allowed.
- Every required model download is complete.
- The chosen language matches the content being spoken or sung.
- AI is not still in its manual-control pause.
If recognition becomes slow or audio queues up, open AI Assistant → Computer setup and use the recommended or lighter setup. Use Settings → AI Assistant → Troubleshooting only when you need the live debug panel.
Privacy
Recognition audio is processed locally. Presenter does not send microphone audio to a cloud transcription service and does not write spoken transcript text to routine logs.