pipecat-ai / multimodal-live-cmdlineLinks
Gemini Multimodal Live command line client
☆12Updated 6 months ago
Alternatives and similar repositories for multimodal-live-cmdline
Users that are interested in multimodal-live-cmdline are comparing it to the libraries listed below
Sorting:
- A demo using Gemini Live where you describe a word and your AI partner tries to guess it☆22Updated 2 months ago
- WhisperAnywhere: Effortless speech-to-text everywhere on your Mac. Use a hotkey to dictate in any app, powered by Whisper AI and Groq API…☆31Updated 9 months ago
- ☆16Updated 9 months ago
- Code Interpreter Replica☆24Updated last year
- Model Context Protocol Servers (Browserbase Version)☆48Updated 7 months ago
- A Next.js chatbot app demonstrating seamless integration with window.ai.☆15Updated 2 years ago
- Generate LLMs.txt files from any website using the CLI + Firecrawl☆35Updated 3 months ago
- A couple scripts to grab stats from email☆43Updated 9 months ago
- An app for generating prompts☆27Updated 5 months ago
- Generate visual podcasts about novels using open source models☆25Updated 2 years ago
- SDK for the Tavily search API which is tailored for LLM agents.☆13Updated last year
- ☆11Updated last year
- Record voice notes & transcribe, summarize, and get tasks☆43Updated last year
- Metal Gear Solid codec calls Chrome extension , with realtime AI & local vector DB☆11Updated 8 months ago
- Radiantloom Email Assist 7B is an email-assistant large language model fine-tuned from Zephyr-7B-Beta, over a custom-curated dataset of 1…☆14Updated last year
- Replicate Flux LoRA image editor.☆51Updated 9 months ago
- An AI-powered Snake game where Claude, an advanced language model, controls the serpent in real-time, showcasing intelligent decision-mak…☆45Updated 7 months ago
- The very first artist assistant☆22Updated last year
- ☆16Updated this week
- A Python package to dynamically load functions for OpenAI Assistant☆54Updated last year
- This repository is an implementation of converting sketches into lively videos using Google's Veo 3 model.☆39Updated this week
- Scrape twitter accounts for fine tuning + merging at high volume☆24Updated 4 months ago
- ☆164Updated this week
- ☆35Updated 6 months ago
- Local & private voice controlled notepad using whisper.cpp☆24Updated last year
- Voice agent using LiveKit (orchestration), Cartesia (TTS), OpenAI (LLM), and Deepgram (STT)☆17Updated 2 weeks ago
- ☆17Updated last year
- make your own NotebookLM clone with OpenAI + ElevenLabs + Cartesia☆34Updated 7 months ago
- Build use cases with VideoDB☆25Updated 3 weeks ago
- Create mini movies from text using fal.ai and ffmpeg-wasm.☆13Updated 10 months ago