fikrikarim/parlor
On-device, real-time multimodal AI. Have natural voice and vision conversations with an AI that runs entirely on your machine. Powered by Gemma 4 E2B and Kokoro.
This project offers a personal AI assistant that you can talk to and show things to using your camera, all running directly on your computer. It takes your spoken questions and camera input, and provides real-time voice responses. Language learners or anyone wanting a private, interactive AI companion would find this useful.
202 stars.
Use this if you want a private, real-time AI conversation partner with both voice and vision capabilities that runs entirely on your own device.
Not ideal if you need an AI for complex tasks like agentic coding or highly specialized professional workflows.
Stars
202
Forks
17
Language
HTML
License
Apache-2.0
Category
Last pushed
Apr 06, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/fikrikarim/parlor"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Agents365-ai/video-podcast-maker
AI-powered video podcast creation skill for coding agents. Supports Bilibili & YouTube,...
Saganaki22/ComfyUI-OmniVoice-TTS
OmniVoice TTS nodes for ComfyUI - Zero-shot multilingual text-to-speech with voice cloning,...
AlexandreSajus/JARVIS
Your own personal voice assistant: Voice to Text to LLM to Speech, displayed in a web interface
team-telnyx/ai
Official one-stop shop for AI Agents and developers building with Telnyx.
tsensei/OpenReels
Open-source AI pipeline that turns any topic into a fully rendered YouTube/Instagram/TikTok...