Skip to main content

Voice-Powered Agent Framework

Project description

Vixio

A streaming voice-powered agent framework based on pipeline architecture

Python 3.12+ License: MIT Status: Alpha

中文文档

Features

  • Pipeline Architecture: Chain multiple stations to form a complete processing flow
  • Station-based Processing: Each station handles specific tasks (VAD/ASR/Agent/TTS)
  • Streaming Support: Real-time audio processing with async queue chains
  • Modular Design: Install only what you need with optional dependencies
  • Multiple Providers: Support for both local inference and cloud services

Requirements

  • Python 3.12 or higher
  • uv (recommended package manager)

Installation

Using uv (Recommended)

  1. Install with core dependencies only:
uv pip install vixio
  1. Install with specific providers:
# For Chinese local development (VAD + ASR + TTS + Agent)
uv pip install "vixio[dev-local-cn]"

# For Qwen platform integration
uv pip install "vixio[dev-qwen]"

# Or install individual components
uv pip install "vixio[xiaozhi,openai-agent,silero-vad-grpc]"

Using pip

pip install vixio

# With optional dependencies
pip install "vixio[dev-local-cn]"

Available Components

Transports

  • xiaozhi - Xiaozhi protocol transport (WebSocket + HTTP)

VAD (Voice Activity Detection)

  • silero-vad-grpc - Silero VAD via gRPC service
  • silero-vad-local - Silero VAD local inference

ASR (Automatic Speech Recognition)

  • sherpa-onnx-asr-grpc - Sherpa-ONNX ASR via gRPC service
  • sherpa-onnx-asr-local - Sherpa-ONNX ASR local inference
  • qwen - Qwen platform ASR

TTS (Text-to-Speech)

  • kokoro-cn-tts-grpc - Kokoro TTS via gRPC service
  • kokoro-cn-tts-local - Kokoro TTS local inference
  • edge-tts - Microsoft Edge TTS (cloud)
  • qwen - Qwen platform TTS

Agent

  • openai-agent - OpenAI-compatible LLM via LiteLLM

Getting Started

  1. Check out the examples/ directory for usage examples
  2. Configure your providers in a YAML config file
  3. Run your voice agent application

For detailed configuration and usage guide, see the documentation.

Project Status

Current Version: v0.1.0 (Alpha)

Note: This project is under active development. APIs may change.

License

MIT License - see LICENSE for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

vixio-0.1.0.tar.gz (183.5 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

vixio-0.1.0-py3-none-any.whl (187.9 kB view details)

Uploaded Python 3

File details

Details for the file vixio-0.1.0.tar.gz.

File metadata

  • Download URL: vixio-0.1.0.tar.gz
  • Upload date:
  • Size: 183.5 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.20

File hashes

Hashes for vixio-0.1.0.tar.gz
Algorithm Hash digest
SHA256 b1f69d9ef607006e6069bd5d61d8b0da0e2e069bed0c1600c05cdff1f5137f5b
MD5 bc102cd48da59c9a9d8024f26a904282
BLAKE2b-256 6fe998bf44ecf02ef34cf290099de880ff49f710b78afa1d526d033aa9c07f0f

See more details on using hashes here.

File details

Details for the file vixio-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: vixio-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 187.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.8.20

File hashes

Hashes for vixio-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 bdaec44caa28604cd4ff7b4017f51bceb3000d5321c5f9079d636ef3024e8444
MD5 a1662af50e3413c4168ad853578a29c9
BLAKE2b-256 1edcd70e8b996746a3307f2ce02240d6faf4986a3c9b40e98a7ed5f55f7fb487

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page