Spaces:
Running
Running
| <html> | |
| <head> | |
| <meta charset="utf-8" /> | |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> | |
| <title>Lyon Chatbox</title> | |
| <link rel="preconnect" href="https://fonts.googleapis.com"> | |
| <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> | |
| <link href="https://fonts.googleapis.com/css2?family=Space+Grotesk:wght@400;500;600;700&family=Manrope:wght@400;500;600&display=swap" rel="stylesheet"> | |
| <link rel="stylesheet" href="style.css" /> | |
| </head> | |
| <body> | |
| <header class="hero"> | |
| <div class="topline"> | |
| <div class="brand"> | |
| <span class="logo">🤖</span> | |
| <span class="brand-name">Reachy Mini</span> | |
| </div> | |
| <div class="pill">Cascade pipeline · Swappable providers · Profiles & reactions</div> | |
| </div> | |
| <div class="hero-grid"> | |
| <div class="hero-copy"> | |
| <p class="eyebrow">ChatBox</p> | |
| <h1>Modular voice conversations for your robot.</h1> | |
| <p class="lede"> | |
| A cascade pipeline — ASR → LLM → TTS — where each stage is a swappable provider. Mix cloud APIs and local models, define personality profiles, trigger live reactions, and let the LLM call tools to dance, emote, or look around. | |
| </p> | |
| <div class="hero-actions"> | |
| <a class="btn primary" href="#highlights">Explore features</a> | |
| <a class="btn ghost" href="#story">See how it feels</a> | |
| </div> | |
| <div class="hero-badges"> | |
| <span>Cascade ASR → LLM → TTS</span> | |
| <span>Local + cloud providers</span> | |
| <span>Live reactions while you speak</span> | |
| <span>LLM tool calls for movement</span> | |
| </div> | |
| </div> | |
| <div class="hero-visual"> | |
| <div class="glass-card"> | |
| <img src="docs/assets/reachy_mini_dance.gif" alt="Reachy Mini dancing" class="hero-gif"> | |
| <p class="caption">Reachy Mini can move, dance, and emote while holding a natural conversation.</p> | |
| </div> | |
| </div> | |
| </div> | |
| </header> | |
| <section id="highlights" class="section features"> | |
| <div class="section-header"> | |
| <p class="eyebrow">What's inside</p> | |
| <h2>A modular conversational layer for your robot</h2> | |
| <p class="intro"> | |
| Each piece of the pipeline is independent and swappable — pick the providers that fit your setup, budget, and latency needs. | |
| </p> | |
| </div> | |
| <div class="feature-grid"> | |
| <div class="feature-card"> | |
| <span class="icon">🔗</span> | |
| <h3>Cascade pipeline</h3> | |
| <p>ASR → LLM → TTS in discrete stages. VAD segments audio, ASR transcribes, LLM reasons, TTS speaks — all streaming.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <span class="icon">🔀</span> | |
| <h3>Swappable providers</h3> | |
| <p>Mix local models (Parakeet, Kokoro) with cloud APIs (Deepgram, Gemini, OpenAI, ElevenLabs). Switch from YAML or CLI flags.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <span class="icon">🎭</span> | |
| <h3>Personality profiles</h3> | |
| <p>Each profile bundles a system prompt, voice, enabled tools, and reaction triggers. Switch profiles live from the Gradio UI.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <span class="icon">⚡</span> | |
| <h3>Live reactions</h3> | |
| <p>Keyword and entity triggers fire while the user is still speaking — the robot reacts before the LLM even sees the text.</p> | |
| </div> | |
| <div class="feature-card"> | |
| <span class="icon">🛠️</span> | |
| <h3>LLM tool calls</h3> | |
| <p>The LLM can dance, play emotions, move the head, peek through the camera, or toggle head-tracking — all via tool calls.</p> | |
| </div> | |
| </div> | |
| </section> | |
| <section id="story" class="section story"> | |
| <div class="story-grid"> | |
| <div class="story-card"> | |
| <p class="eyebrow">How it feels</p> | |
| <h3>From config to conversation in one command</h3> | |
| <ul class="story-list"> | |
| <li><span>⚙️</span> Pick your providers in cascade.yaml — local ASR, cloud LLM, local TTS, or any mix.</li> | |
| <li><span>🗣️</span> Start talking and watch streaming transcripts appear in the Gradio UI.</li> | |
| <li><span>⚡</span> The robot reacts to keywords instantly — before your sentence even finishes.</li> | |
| <li><span>💃</span> Ask for a dance or an emotion; the LLM calls tools and the robot moves.</li> | |
| </ul> | |
| </div> | |
| <div class="story-card secondary"> | |
| <p class="eyebrow">Where it shines</p> | |
| <h3>Demos, teaching, and custom robot personalities</h3> | |
| <p class="story-text"> | |
| Build a pirate-themed guide, a museum docent, or a classroom assistant — each with its own voice, tools, and live reactions. Swap providers to balance cost and latency, run fully local on Apple Silicon, or mix in cloud APIs for maximum quality. | |
| </p> | |
| <div class="chips"> | |
| <span class="chip">Cascade pipeline</span> | |
| <span class="chip">Local + cloud mix</span> | |
| <span class="chip">Profiles</span> | |
| <span class="chip">Live reactions</span> | |
| <span class="chip">Tool calls</span> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <footer class="footer"> | |
| <p> | |
| Lyon Chatbox by <a href="https://github.com/pollen-robotics" target="_blank" rel="noopener">Pollen Robotics</a>. | |
| Explore more apps on <a href="https://huggingface.co/spaces/pollen-robotics/Reachy_Mini_Apps" target="_blank" rel="noopener">Hugging Face Spaces</a>. | |
| </p> | |
| </footer> | |
| </body> | |
| </html> | |