rtk-ai/vox
A universal AI toolkit for high-performance Speech-to-Text (STT) and Text-to-Speech (TTS) processing, designed for low-latency and easy model integration.
Supports five pluggable TTS backends (macOS `say`, ONNX-based `kokoro`, Rust/Candle `qwen-native`, PyTorch `voxtream`, and MLX `qwen`) with zero-shot voice cloning on three of them, achieving 2–3s warm latency on Apple Silicon and 19s on CUDA. Built in Rust with Python interop, exposes a daemon mode for persistent model loading, and integrates as an MCP server or CLI tool into 14+ AI coding assistants (Claude Code, Cursor, VS Code, Zed). Includes SQLite state tracking, interactive TUI configuration, and voice recording/cloning workflows entirely offline.
Stars
36
Forks
1
Language
Rust
License
—
Category
Last pushed
Mar 07, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/rtk-ai/vox"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
alphacep/vosk-api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
huggingface/speech-to-speech
Build local voice agents with open-source models
linto-ai/WebVoiceSDK
Buildings block for voice-enabled applications in the browser
Picovoice/speech-to-text-benchmark
speech to text benchmark framework
vox-serve/vox-serve
A Streaming-Native Serving Engine for TTS/STS Models