docs(readme): tighten latency budget to <=1s, STT via Discord voice, Korean human-like TTS

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-08-11 17:52:00 +09:00
parent b0ab23909e
commit 1eb6620eb3
2 changed files with 41 additions and 22 deletions
--- a/requirements.txt
+++ b/requirements.txt
@@ -9,9 +9,9 @@
 # anthropic

 # --- planned voice backends (not yet implemented) ---
-# faster-whisper      # STT
-# sounddevice         # mic capture
-# (a TTS engine, e.g. MeloTTS)
+# faster-whisper      # STT (input = Discord voice reception, not a local mic)
+# (Opus decode for Discord voice audio, e.g. via the selfbot/ffmpeg path)
+# (a Korean TTS engine, e.g. MeloTTS)

 # --- dev ---
 # pytest