xiaozhi-esp32 vs Voicebox
Two of the top projects in Voice, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
xiaozhi-esp32
ESP32 firmware for a voice chatbot with MCP device and cloud tool control
Voicebox
Local voice studio for cloning, TTS, dictation and agent speech
Verdict
xiaozhi-esp32 ranks higher, 80 to 71. Of the 3 score parts we measure for both, xiaozhi-esp32 leads on 1, Voicebox on 1 and 1 is even.
- AdoptionVoicebox leads by 14 points, 91 to 77.
- FreshnessEven at 100.
- MaintenanceWe do not score xiaozhi-esp32 on this; Voicebox has 54.
- Easy to runWe do not score xiaozhi-esp32 on this; Voicebox has 67.
- Agent-readyxiaozhi-esp32 leads by 30 points, 30 to 0: a wide gap.
Pick xiaozhi-esp32 if you are
Hardware hobbyists and embedded engineers building ESP32 voice assistants
- Supports 138 board directories and 171 release variants across ESP32, C3, C5, C6, S3 and P4
- Documented WebSocket and MQTT+UDP protocols let third-party servers and clients interoperate
Pick Voicebox if you are
Individuals wanting local voice cloning, TTS and dictation
- Eight switchable TTS engines; Chatterbox Multilingual covers 23 languages
- REST API plus HTTP and stdio MCP server for Claude Code, Cursor, Windsurf
| What we compare | xiaozhi-esp32 | Voicebox |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 77, popular | 91, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | Not scored for this kind | 54, fair |
| Easy to run | Not scored for this kind | 67, easy |
| Agent-ready | 30, minimal | 0, none |
| Facts from GitHub and the README | ||
| Stars | 31.7k | 58.2k |
| License | MIT (permissive) | MIT (permissive) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Oct 2026 | Apr 2026 |
| Language | C++ | Python |
| Docker | No | Yes |
| GPU | Not needed | Optional |
| arm64 or Apple Silicon | Not stated | Mentioned |
xiaozhi-esp32
C++ firmware that turns ESP32 boards into a voice chatbot. It does offline wake-word detection with ESP-SR and streams Opus audio over WebSocket or MQTT+UDP to a server that handles ASR, LLM and TTS. MCP is used on the device (speaker, LED, servo, GPIO) and in the cloud (smart home, email, search). It connects to the hosted xiaozhi.me server by default, and self-hosted server projects are listed.
Who it is for: Hardware hobbyists and embedded engineers building ESP32 voice assistants
Strengths
- Supports 138 board directories and 171 release variants across ESP32, C3, C5, C6, S3 and P4
- Documented WebSocket and MQTT+UDP protocols let third-party servers and clients interoperate
- Offline wake-word detection with customizable wake words; Wi-Fi, Ethernet and Cat.1 4G networking
- Prebuilt firmware can be flashed without setting up a development environment
Weaknesses
- Models do not run on the device; a server is needed for ASR, LLM and TTS
- Default setup depends on the hosted xiaozhi.me service and an account
- Requires ESP-IDF 6.0.1 or later; 5.x is unsupported and the v6.1 tag has a reported C3 Wi-Fi bug
- Beginner tutorials are on Feishu and bilibili, mostly in Chinese
- no GPU
- Needs ESP-IDF 6.0.1+, ESP32 board, xiaozhi.me or compatible server
- Models: Qwen, DeepSeek, Realtime end-to-end voice models
Voicebox
Desktop app (Tauri) and Docker service that clones voices from a short sample and generates speech through eight TTS engines, including Qwen3-TTS, Chatterbox and Kokoro, in 23 languages. Adds Whisper dictation with a global hotkey, a REST API on port 17493 and an MCP server so coding agents can speak in a cloned voice. For individuals who want ElevenLabs-style voice I/O on their own machine.
Who it is for: Individuals wanting local voice cloning, TTS and dictation
Strengths
- Eight switchable TTS engines; Chatterbox Multilingual covers 23 languages
- REST API plus HTTP and stdio MCP server for Claude Code, Cursor, Windsurf
- Runs on MLX, CUDA, ROCm, DirectML, Intel Arc or CPU
- Auto-chunking with crossfade handles scripts up to 50,000 characters
Weaknesses
- No prebuilt Linux binaries; build from source or use Docker
- Only Chatterbox Turbo honors tags like [laugh]; other engines read them aloud
- Dictation auto-paste and the permission flow are macOS-specific
- Docker deployment gets one line in the README; details are in external docs
- GPU optional
- Docker + Compose
- Models: Qwen3-TTS 0.6B/1.7B, Qwen CustomVoice, Qwen VoiceDesign, LuxTTS, Chatterbox Multilingual
- port 17493
- README: alternative to ElevenLabs
More in Voice
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.