ed/rook
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

chore(deps): dearpygui->imgui-bundle, add google-cloud-texttospeech and openai for STT/TTS

Browse Source
This commit is contained in:
Edward R. Gonzalez
2026-03-01 22:45:53 -05:00
parent a80b31f1d9
commit 2df984ac4c
3 changed files with 475 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
CLAUDE.md
View File

@@ -146,9 +146,9 @@ After completing a group of related tasks (a "phase"):
- **Language**: Python 3.11+
- **Package manager**: `uv`
- **AI**: Anthropic Claude — `claude-haiku-4-5-20251001` primary, `claude-sonnet-4-6` fallback for complex reasoning
- **Voice In**: Discord audio attachments → STT (discord.py bot, `DISCORD_BOT_TOKEN` env var)
- **Voice Out**: ElevenLabs TTS (Rook voice ID — scratchy/rough robot) with Google TTS as fallback
- **GUI** (ModernCoSy component): Dear PyGui — dockable panels, dark theme
- **Voice In**: Discord audio attachments → STT (`discord.py` bot, `DISCORD_BOT_TOKEN` env var). STT: OpenAI Whisper (`openai`) or Google Cloud STT — pluggable via `STT_BACKEND` env var (`whisper`/`google`)
- **Voice Out**: ElevenLabs TTS (Rook voice ID — `ELEVENLABS_VOICE_ID` env var) with Google Cloud TTS as fallback (`GOOGLE_TTS_KEY` env var)
- **GUI**: `imgui-bundle` (NOT dearpygui — dearpygui has multi-viewport issues). Dockable panels, dark theme.
- **CoSy**: subprocess stdin/stdout pipe to `CoSy.bat` / `reva.exe`
- **Testing**: pytest + pytest-cov