Eloquent

The most feature-complete local AI workstation. No subscriptions. No cloud dependency. Just your hardware.

While everyone else ships another chat UI with fancy presets, Eloquent gives you in-house Stable Diffusion, multi-GPU inference, voice cloning, model ELO testing, a tool-calling code editor, multi-role chat, and forensic linguistics – all running locally.

Optional cloud APIs for when you want them. Your choice.

What makes it different?

• Single application: LLM + image generation + voice + code tools + model evaluation
• Multi-GPU that works: Unified tensor splitting or dedicated GPU assignment
• More than chat: ELO testing framework, forensic linguistics, story state tracking, multi-role conversations
• Production features: Voice cloning, image upscaling, conversation summaries, agent mode

---

⚡ Quick Start

| I want to... | Do this | |--------------|---------| | Chat with voice | install.bat → run.bat → load a GGUF → enable Auto-TTS | | Generate images | Drop .safetensors in a folder → Settings → Image Gen → set path | | Upscale images | Generate image → click Upscale → select 2x/3x/4x | | Multi-character roleplay | Settings → enable Multi-Role → add characters to roster | | Test models | Model Tester → import prompts → run A/B with ELO ratings | | Edit code with AI | Load Devstral → Code Editor → set project directory | | Play chess (AI + personality) | Chess tab in navbar (Stockfish installed automatically by install.bat) | | Clone a voice | Settings → Audio → Chatterbox Turbo → upload reference |

---

👥 Who This Is For

Power users with NVIDIA GPUs who want a complete local AI stack instead of juggling 5 different tools.

Roleplayers & writers who need multi-character conversations, story state, portraits, and voice in one app.

Model evaluators who want ELO testing and judge orchestration without building research infrastructure.

Privacy-first users who don't want conversations leaving their machine.

Not for you if:

• You don't have an NVIDIA GPU
• You're on Mac or Linux (Windows only)

---

🎯 Core Features

Chat & Roleplay

Multi-Role Conversations

• Multiple characters in one chat with automatic speaker selection
• Per-character TTS voices and talkativeness weights
• Optional narrator with customizable interjection frequency
• User profile picker for switching between personas
• Group scene context for shared settings

Story Management

• Story Tracker: Characters, locations, inventory, objectives injected into AI context
• Scene Summary: Persistent context that grounds the AI in current mood and situation
• Choice Generator: Contextual actions with 6 behavior modes (Dramatic, Chaotic, Romantic, etc.)
• Director Mode: Toggle between character actions and narrative beats for plot steering
• Conversation Summaries: Save summaries and load them into fresh chats for continuity

Standard Features

• Character library and creator with AI-generated portraits
• Memory & RAG with document ingestion and web search
• Author's Note for direct AI guidance
• Focus Mode and Call Mode interfaces

Inference & Models

Multi-GPU Support

• Unified tensor splitting across 2, 3, 4+ GPUs
• Split-services mode with dedicated GPU assignments
• Purpose slots for judge models and memory agents
• Real-time VRAM monitoring

Model Compatibility

• Local GGUF models via llama.cpp
• OpenAI-compatible APIs (OpenRouter, local proxies, Chub.ai)
• Simultaneous local + API model usage

Image Generation

Local Stable Diffusion

• SD 1.5, SDXL, and FLUX support (safetensors/ckpt/gguf)
• Custom ADetailer with YOLO face detection and inpainting
• "Visualize Scene" - auto-generate images from chat context
• Set generated images as chat backgrounds

Image Upscaling

• Variable upscaling: 2x, 3x, 4x with ESRGAN models
• Model selector for different upscaler weights

Cloud Fallback (Optional)

• NanoGPT API for image generation without local GPU
• Experimental video generation (pay-per-use)

Voice & Audio

TTS Engines

• Kokoro: Fast neural synthesis with multiple voices
• Chatterbox: Voice cloning from reference samples
• Chatterbox Turbo: Enhanced cloning with paralinguistic cues ([laugh], [sigh], [cough])

Features

• Chunked streaming pipeline for low latency
• Auto-TTS with one-click toggle
• Call Mode: Full-screen voice conversation with animated avatars
• Per-character voice assignment in multi-role chat

Model Evaluation

ELO Testing Framework

• Single model testing against prompt collections (MT-Bench, custom)
• A/B head-to-head comparisons with ELO updates
• Dual-judge mode with reconciliation
• Character-aware judging with custom evaluation criteria
• Parameter sweeps (temperature, top_p, top_k)
• 14 built-in analysis perspectives including 6-Year-Old Transformer Boy, Al Swearengen, Bill Burr, Alex Jones
• Import/export results with full metadata

Code Editor

Tool-Calling Agent

• Devstral Small 2 24B (local) or Devstral Large (OpenRouter)
• File operations with automatic .bak backups
• Shell execution (optional, sandboxed)
• Vision support via screenshots

Agent Mode Features

• Chain of Thought visualization - see reasoning before actions
• Hallucination Rescue - executes intended tools even when JSON parsing fails
• Loop detection prevents endless file reading
• File explorer with full drive navigation

Security

• Sandboxed to working directory
• Optional command execution
• Automatic backups on file writes

Analysis & Tools

Forensic Linguistics

• Authorship analysis and stylistic comparison
• Pluggable embedding models (BGE-M3, GTE, RoBERTa, Jina, Nomic)
• Build corpora from documents or scraped text

UI & Customization

• 5 premium themes: Claude, Messenger, WhatsApp, Cyberpunk, ChatGPT Light
• Text formatting: Quote highlighting, H1-H3 headings, paragraph controls
• Auto-save settings (directories require manual save)

Mobile Support

Full mobile optimization for phones and tablets.

• Responsive design with touch-friendly UI throughout
• Universal access: automatic 0.0.0.0 binding and IP discovery for local network connection
• Native audio handling for reliable TTS on iOS and Android
• Mobile-first themes (Messenger, WhatsApp) designed for phone/tablet use
• Touch-optimized controls and adaptive layouts

---

🖼️ Screenshots

Main Chat

Full chat with Story Tracker, Choice Generator, streaming TTS, and model control.

Audio Control

Voice cloning with real-time streaming playback.

Focus Mode

Distraction-free interface.

Character Library

AI-generated character portraits via built-in Stable Diffusion.

ELO Tester

Professional model evaluation with dual-judge reconciliation.

Mobile Themes

---

🚀 Installation

Prerequisites

• Windows 10/11 (64-bit)
• NVIDIA GPU with CUDA support
• Python 3.11 or 3.12
• Node.js v21.7.3 (recommended). Node 22 is untested; if the backend window closes when you use Browse for model/directory settings, try Node 21.7.3 or type the folder path manually.

VRAM Guide

| Use Case | Recommended VRAM | |----------|------------------| | Small models (7B Q4) | 8GB | | Medium models (13B-20B) | 12GB | | Large models (70B+) | 24GB+ or multi-GPU | | SD 1.5 | 4GB+ | | SDXL/FLUX | 8GB+ | | LLM + image gen together | 16GB+ or split across GPUs |

Install & Run

git clone https://github.com/boneylizard/Eloquent
cd Eloquent
install.bat    # Wait for completion (5-10 minutes)
run.bat

The installer handles everything: Python venv, PyTorch with CUDA 12.1, pre-built wheels, all dependencies.

Default ports:

• Backend: http://localhost:8000
• TTS: http://localhost:8002
• Frontend: http://localhost:5173

Port conflicts are handled automatically - the frontend discovers actual ports.

---

⚙️ Configuration

Models

1. Settings → Model Settings → set GGUF directory
2. Model Selector → choose per-GPU or unified multi-GPU
3. Add OpenAI-compatible API endpoints if desired

Images

1. Settings → Image Generation → set safetensors directory
2. ADetailer Models → point to YOLO .pt files
3. Upscaler Models → point to ESRGAN .pth files

Voice

1. Settings → Audio → choose Kokoro or Chatterbox/Chatterbox Turbo
2. For cloning: upload reference sample
3. Enable Auto-TTS toggle in chat

Multi-Role

1. Settings → enable Multi-Role Chat
2. Click roster button → add characters
3. Set talkativeness weights and voices
4. Optionally enable narrator

Chess (Stockfish)

The Chess tab uses Stockfish for analysis. **Fresh installs