ShaerWare/AI_Secretary_System
π ΠΠΎΠΊΠ°Π»ΡΠ½ΡΠΉ AI-ΡΠ΅ΠΊΡΠ΅ΡΠ°ΡΡ, ΡΠ΅Ρ . ΠΏΠΎΠ΄Π΄Π΅ΡΠΆΠΊΠ° ΠΈ ΠΌΠ΅Π½Π΅Π΄ΠΆΠ΅Ρ ΠΏΠΎ ΠΏΡΠΎΠ΄Π°ΠΆΠ°ΠΌ Ρ ΠΊΠ»ΠΎΠ½ΠΈΡΠΎΠ²Π°Π½ΠΈΠ΅ΠΌ Π³ΠΎΠ»ΠΎΡΠ° XTTS v2, real-time ΡΠ°ΡΠΏΠΎΠ·Π½Π°Π²Π°Π½ΠΈΠ΅ΠΌ ΡΠ΅ΡΠΈ (Vosk/Whisper) ΠΈ offline LLM (vLLM + Qwen/Llama ΠΈ ΡΠΏ). ΠΠΎΠ»Π½ΠΎΡΠ΅Π½Π½Π°Ρ Π°Π΄ΠΌΠΈΠ½-ΠΏΠ°Π½Π΅Π»Ρ (Vue 3), Telegram-Π±ΠΎΡ, Π²ΠΈΠ΄ΠΆΠ΅Ρ Π΄Π»Ρ ΡΠ°ΠΉΡΠ°, fine-tuning pipeline. Self-hosted, ΠΏΡΠΈΠ²Π°ΡΠ½ΠΎΡΡΡ Π΄Π°Π½Π½ΡΡ , Π‘ΠΠ‘ ΠΈ ΡΠ΅Π»Π΅ΡΠΎΠ½Π½ΡΠ΅ Π·Π²ΠΎΠ½ΠΊΠΈ .
Integrates with Telegram/WhatsApp for multi-instance bot deployments, vLLM inference engine serving Qwen/Llama models with LoRA fine-tuning pipeline, and amoCRM via REST API for sales funnel automation. The architecture uses modular 28-router design with separate microservice instances (TTS, STT, voice cloning, fine-tuning) communicating through SQLite + Redis, supporting local-first operation with optional cloud LLM fallbacks (Gemini, Claude, OpenAI) while maintaining data control through local embeddings and configurable RAG policies.
Stars
5
Forks
5
Language
Python
License
MIT
Category
Last pushed
Mar 12, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/ShaerWare/AI_Secretary_System"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
bolna-ai/bolna
Conversational voice AI agents
SaynaAI/sayna
Sayna is a unified Voice Layer for AI Agents with a seemless integration to an existing agentic...
MCERQUA/OpenVoiceUI
Open voice UI shell for AI agents. Bring any LLM, TTS, or framework β handles voice I/O, Agent...
jesuscopado/samantha-os1-openai-realtime
Samantha OS1 is a conversational AI assistant powered by the Realtime API from OpenAI
Anil-matcha/AI-Voice-Agent
Self-hosted AI voice agent