| 1 | # Whisper STT Plugin DOX |
| 2 | |
| 3 | ## Purpose |
| 4 | |
| 5 | - Own built-in Whisper speech-to-text integration, microphone runtime settings, and transcription delivery behavior. |
| 6 | |
| 7 | ## Ownership |
| 8 | |
| 9 | - `api/` owns transcribe and status endpoints. |
| 10 | - `helpers/` owns runtime and migration behavior. |
| 11 | - `hooks.py` owns provider registration/lifecycle behavior. |
| 12 | - `webui/` owns settings, main speech UI, store, and styling. |
| 13 | - `default_config.yaml`, `plugin.yaml`, and `README.md` own defaults, metadata, and behavior notes. |
| 14 | |
| 15 | ## Local Contracts |
| 16 | |
| 17 | - Keep dependency installation and model bootstrap on Docker/bootstrap paths. |
| 18 | - Preserve configured message mode, language, silence threshold, silence duration, and waiting timeout behavior. |
| 19 | - Keep all `data-whisper-microphone` controls synchronized with the same microphone status. |
| 20 | - Optional final-transcript handlers must receive the configured draft/send mode without changing the main chat microphone's delivery behavior. |
| 21 | - Do not expose raw audio or transcriptions beyond intended UI/API paths. |
| 22 | |
| 23 | ## Work Guidance |
| 24 | |
| 25 | - Coordinate status endpoint behavior with frontend microphone and transcription state. |
| 26 | |
| 27 | ## Verification |
| 28 | |
| 29 | - Smoke-test status, transcription, model/language settings, send/draft modes, and silence handling after changes. |
| 30 | |
| 31 | ## Child DOX Index |
| 32 | |
| 33 | No child DOX files. |