mezbaul-h/june
Local voice chatbot for engaging conversations, powered by Ollama, Hugging Face Transformers, and Coqui TTS Toolkit
Provides flexible interaction modes spanning text-only, voice input with text output, text input with audio output, and full bidirectional voice—all configurable via JSON to selectively disable STT or TTS components. Orchestrates three independent ML pipelines (Ollama for LLM inference, Hugging Face Whisper for speech recognition, Coqui TTS for synthesis) with per-component device assignment (CPU/CUDA/MPS) and optional chat history. Supports voice cloning through compatible Coqui models and remote Ollama instances via environment variables.
784 stars. No commits in the last 6 months.
Stars
784
Forks
52
Language
Python
License
MIT
Category
Last pushed
Aug 12, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/mezbaul-h/june"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digiteinfotech/kairon
Agentic AI platform that harnesses Visual LLM Chaining to build proactive digital assistants
withcatai/catai
Run AI ✨ assistant locally! with simple API for Node.js 🚀
bigsk1/voice-chat-ai
🎙️ Speak with AI - Run locally using Ollama, OpenAI, Anthropic or xAI - Speech uses SparkTTS,...
syxanash/maxheadbox
Tiny truly local voice-activated LLM Agent that runs on a Raspberry Pi
AmberSahdev/Open-Interface
Control Any Computer Using LLMs.