asepharyana a3a91aa2ce feat(voice): auto-detect speech language for transcription (drop forced 'en') ...

Whisper previously hardcoded language:en, mis-transcribing id/en-mixed
speech. Omitting 'language' makes Whisper auto-detect. Paired with enabling
AI_VOICE_TRANSCRIPTION_ENABLED (BWS secret gmw_ai_voice_transcription_enabled
= true) so new recordings are transcribed.

Spec: .hermes/plans/2026-08-30_recordings-v2-features-spec.md

2026-08-30 13:28:17 +07:00

..

backend

build(deps-dev): bump @types/node

2026-08-28 14:25:12 +00:00

discord-gateway

feat(voice): auto-detect speech language for transcription (drop forced 'en')

2026-08-30 13:28:17 +07:00

frontend

feat(frontend): filter recordings per-speaker + export WAV for Audacity

2026-08-30 12:59:46 +07:00