Voxcpm2 Voice Server — AI skill for Claude Code
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/speechworks 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
doctorthat explains problems in plain English, Docker, a systemd service, and launchd support
Contents
- Requirements
- Install: Windows · Linux · macOS · Docker
- Using the web app
- Connect your AI agents
- Emotion markers
- API
- Settings
- Updating & uninstalling
- Troubleshooting
- 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+ |
Related Skills
Dettivo Linux
Private, offline speech-to-text for Linux: push-to-talk dictation into any app, meeting transcription with spe
EmotionVoice
Local web app + CLI for emotional AI text-to-speech and voice cloning with the Fish Audio API. 60+ emotion tag
JustDay
Your own JARVIS for Linux: a voice-and-keyboard AI agent for KDE Plasma 6 that does things — apps, windows, mu
Multimodal Voice Assistant
This project is a multi-modal AI voice assistant that uses LM Studio, OpenAI API or Claude Code, audio process
Soundbox
Free, open-source, local alternative to ElevenLabs and Suno. AI sound effects, music with lyrics, text-to-spee
Vocal Composer
Voice-First Writing with AI 2026 – Real-Time Speech-to-Text for Claude Code & Cowork
Related Agents
Office DevOps
Office worker. Builds, packaging, CI, release — installers (Windows/macOS), app bundles, GitHub Actions, versi
Bash Scripter
Use this agent when you need to write or fix bash/shell scripts — entrypoints, setup scripts, statusline scrip
Byok Token Security Expert
BYOK (Bring-Your-Own-Key) and OAuth token security expert. Deep on cross-platform OS keychain integration (mac