Real-Time Voice AgentsfreeNew

XiaoZhi AI

Open-source ESP32 voice chatbot with wake word, Opus streaming and a display

Visit XiaoZhi AI

What XiaoZhi AI does

  • Open-source ESP32 voice chatbot with wake word, Opus streaming and a display
  • Free official server lets personal users try a Qwen real-time model after registering
  • Device-side and cloud MCP for controlling IoT gadgets
  • MIT licensed firmware supporting many ESP32 chips

XiaoZhi AI — straight answers

What is XiaoZhi AI?

XiaoZhi AI is listed under Real-Time Voice Agents, in the AI Agents & Automation category on Flocci AI Tools. Open-source ESP32 voice chatbot with wake word, Opus streaming and a display. It is free, with no paid plan attached, and it lives at xiaozhi.me.

Is XiaoZhi AI free?

XiaoZhi AI is listed as fully free — there is no paid tier attached to it in the catalog. That makes it one of the 399 entries on Flocci AI Tools with no upgrade path built in.

What can XiaoZhi AI do?

XiaoZhi AI does 4 things the catalog singles out: Open-source esp32 voice chatbot with wake word, opus streaming and a display; free official server lets personal users try a qwen real-time model after registering; device-side and cloud mcp for controlling iot gadgets; mit licensed firmware supporting many esp32 chips.

What is the best free alternative to XiaoZhi AI?

Bolna is the closest free alternative: it sits in the same Real-Time Voice Agents sub-category and is free. Kyutai Unmute, LiveKit Agents and Pipecat also start free. The full list is on the alternatives page.

See the full list →

XiaoZhi AI alternatives

Compare all alternatives →

Vapi

Real-Time Voice Agents
freemiumLeaving soon
  • Orchestrates STT/LLM/TTS providers of choice into one low-latency voice-agent pipeline
  • Usage-based per-minute pricing with free trial minutes included
  • SOC 2/HIPAA/PCI compliance add-ons for regulated call-center deployments
Visit

Retell AI

Real-Time Voice Agents
freemiumLeaving soon
  • Free starting credit with no contract required
  • Supports swapping GPT, Claude or Gemini as the reasoning layer per agent
  • Batch calling campaigns plus live AI-to-human call transfer built in
Visit

Bland AI

Real-Time Voice Agents
freemiumLeaving soon
  • All-in-one per-minute pricing bundles LLM+STT+TTS with no separate token pass-through charges
  • Free start with call credits plus an inbound number included
  • Tiered platform fees (Build/Scale) unlock lower per-minute rates for high volume
Visit

LiveKit Agents

Real-Time Voice Agents
free
  • Apache-2.0 open-source framework, fully self-hostable on your own servers
  • Native WebRTC client support across web/mobile/telephony out of the box
  • Native Model Context Protocol (MCP) support for tool-using voice agents
Visit

Pipecat

Real-Time Voice Agents
free
  • BSD-2-Clause open-source Python framework for real-time voice/multimodal agents
  • Supports distributed multi-agent systems with handoffs over a shared bus
  • Maintained by Daily with an active plugin ecosystem for STT/LLM/TTS providers
Visit

Ultravox

Real-Time Voice Agents
freemiumLeaving soon
  • Speech-native processing skips the STT-to-text bottleneck, preserving tone/cadence/pitch
  • Free tier: 5¢/min including TTS for up to 5 concurrent calls
  • Open-weight models (fixie-ai) published on Hugging Face for research use
Visit

Head-to-head comparisons

XiaoZhi AI vs VapiXiaoZhi AI vs Retell AIXiaoZhi AI vs Bland AIXiaoZhi AI vs LiveKit AgentsXiaoZhi AI vs PipecatXiaoZhi AI vs Ultravox