esprit112

Voxcpm2 Voice Server — AI skill for Claude Code

AI community

Private, studio-quality local text-to-speech (VoxCPM2): web app, OpenAI-compatible API, one-click installers for Windows/Linux/macOS, and voice for AI agents (Hermes, OpenClaw, Claude Code, Codex, Gem.

How to install Voxcpm2 Voice Server

This entry records only its repository, not the path inside it, so there is no exact command to give. Open esprit112/voxcpm2-voice-server and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Voxcpm2 Voice Server does

Private, studio-quality local text-to-speech (VoxCPM2): web app, OpenAI-compatible API, one-click installers for Windows/Linux/macOS, and voice for AI agents (Hermes, OpenClaw, Claude Code, Codex, Gemini CLI, OpenCode, Open WebUI)

Alternatives in AI

  • Om Humanize — Voice-calibrated editing — makes Claude-drafted text sound like you wrote it, not like AI wrote it 4.6k ★
  • Devo — Model-neutral agent desktop/runtime for private, enterprise, and OpenAI-compatible / Anthropic-compatible mode 316 ★
  • Guaardvark — The self-hosted AI studio: local video, image, music, voice, LoRA training, coding swarms, RAG and screen agen 211 ★

README

VoxCPM2 Voice Server

**Private, studio-quality text-to-speech that runs on your own computer.** A web app for making voices, an OpenAI-compatible API for your tools, and one-command hookups that give your AI agents (Hermes, OpenClaw, Claude Code, Codex, Gemini CLI, OpenCode, Cursor, Open WebUI, …) a real voice.

Powered by [VoxCPM2](https://huggingface.co/openbmb/VoxCPM2) from OpenBMB: 48 kHz audio, 30 languages, voice design from a text description, and voice cloning from a few seconds of audio.

  • 🎙️ 8 ready-made voices, plus voices you design ("a warm elderly Scottish storyteller") or clone
  • 🎭 Inline emotion markers: [excited] We won! [pause:500ms] [whisper] Don't tell anyone.
  • 🔌 Drop-in OpenAI API: POST /v1/audio/speech works with any OpenAI TTS client
  • 🖥️ Windows 11, Linux and macOS (Apple Silicon), on NVIDIA, AMD (ROCm), Intel Arc, Apple GPUs, or CPU
  • 🔒 Offline and private: after the one-time model download nothing leaves your machine
  • 🧰 One-click installers, a doctor that explains problems in plain English, Docker, a systemd service, and launchd support

Contents

  1. Requirements
  2. Install: Windows · Linux · macOS · Docker
  3. Using the web app
  4. Connect your AI agents
  5. Emotion markers
  6. API
  7. Settings
  8. Updating & uninstalling
  9. Troubleshooting
  10. Project layout · Licence & responsible use

Requirements

Minimum Recommended
OS Windows 10 1809+, Ubuntu 20.04+ / any modern Linux, macOS 13+ (Apple Silicon) Windows 11, Ubuntu 22.04+, macOS 14+
GPU none (CPU works, slowly) NVIDIA with 8 GB+ VRAM (RTX 3060 or better), Apple M-series with 16 GB+
RAM 8 GB 16 GB+