- 21:14:02 DEBUG Live API opened
- 21:14:02 DEBUG setup completed (from server)
- 21:14:05 DEBUG VAD: speech started.
- 21:14:07 DEBUG VAD: speech ended.
- 21:14:07 DEBUG activity end sent
- 21:14:08 DEBUG Starting discord audio stream
- 21:14:11 DEBUG turn complete
Voice & Generation Bridge. Chat + Grounding: 60-msg context. Live Voice Loop: 24 kHz → 48 kHz. Speech Synthesis: 24 voices.
Geminiero: Multimodal AI Inside a Discord Server
Four Gemini capabilities (chat, image generation, speech and live voice) behind one bot, reachable by slash command or a single-character prefix. The hard part is the voice loop: Discord speaks Opus at 48 kHz stereo, Gemini Live speaks PCM at 24 kHz mono, and neither waits for the other.
- Bidirectional live voice with VAD turn-taking
- 4 capabilities · 2 interfaces each
- Context persisted in SQLite (WAL)
STACK: TypeScript · Bun · discord.js · @google/genai · SQLite · Opus