Naiyuan Qing 4e5780692e feat(media): transcribe audio via Whisper API before reaching agent ... Move audio transcription from agent-driven (exec + local whisper) to Manager-layer processing via OpenAI Whisper API. Voice messages are now transcribed automatically before the agent sees them, so the agent only receives text. Local whisper skill remains as fallback when API key is not configured. Also changed default model from turbo to base for faster first-time experience. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>		2026-02-09 10:06:11 +08:00
..
code-review	feat(agent): add skills system with profile integration (#21)	2026-01-30 05:21:57 +08:00
commit	feat(agent): add skills system with profile integration (#21)	2026-01-30 05:21:57 +08:00
profile-setup	refactor(profile-setup): simplify setup to focus on agent identity and user info	2026-02-01 23:59:59 +08:00
skill-creator	docs(skill-creator): support profile-specific skill creation	2026-01-31 18:53:27 +08:00
whisper	feat(media): transcribe audio via Whisper API before reaching agent	2026-02-09 10:06:11 +08:00