voice-tool / README.md
ameliakris's picture
Initial HF Spaces deployment
30ea74d
---
title: Voice Development Assistant
emoji: 🎀
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 6.0.1
app_file: app.py
pinned: false
license: mit
hardware: zero-a10g
---
# 🎀 Voice Development Assistant
Personal voice interface for development workflows with:
- **Speech-to-Text**: Whisper (GPU accelerated via ZeroGPU)
- **Text-to-Speech**: HuggingFace SpeechT5 (free, no API key)
- **LLM Chat**: OpenRouter (Claude, GPT-4, etc.)
## Setup
1. Add your `OPENROUTER_API_KEY` as a Space secret
2. Get your key at [openrouter.ai](https://openrouter.ai)
## Features
- 🎀 Voice Chat - Speak with AI assistants
- πŸ“ Transcribe - Convert speech to text
- πŸ”Š Speak - Generate natural speech from text
- πŸ’¬ Text Chat - Traditional chat interface
## Configuration (Optional Environment Variables)
- `OPENROUTER_API_KEY` - Required for LLM features
- `WHISPER_MODEL` - Whisper model size (default: base)
- `LLM_MODEL` - OpenRouter model (default: anthropic/claude-sonnet-4-20250514)
- `LANGUAGE` - Speech language (default: en)