wwbin2017/bailing
An open-source voice assistant that combines ASR, LLM, and TTS to enable natural speech-to-speech conversation with tool-calling capabilities.

百聆 (Bailing) is a voice conversation robot that mimics GPT-4o’s speech interaction capabilities. It integrates automatic speech recognition (ASR), large language models including DeepSeek R1, and text-to-speech synthesis (TTS) into a unified pipeline. The system uses OpenClaw as its core tool-calling engine to handle complex tasks, external tool orchestration, and high-level agent capabilities. It targets edge devices and low-resource environments, achieving end-to-end latency of around 800ms without requiring GPU hardware.
Frequently asked
- What is wwbin2017/bailing?
- An open-source voice assistant that combines ASR, LLM, and TTS to enable natural speech-to-speech conversation with tool-calling capabilities.
- Is bailing open source?
- Yes — wwbin2017/bailing is open source, released under the MIT license.
- What language is bailing written in?
- wwbin2017/bailing is primarily written in Python.
- How popular is bailing?
- wwbin2017/bailing has 1.7k stars on GitHub.
- Where can I find bailing?
- wwbin2017/bailing is on GitHub at https://github.com/wwbin2017/bailing.