Stats
Actions
Tags
From voicemode
Enables remote voice conversations in Claude Code via VoiceMode Connect cloud platform. Connects agents to iOS app or web clients over MCP without local STT/TTS setup.
How this skill is triggered — by the user, by Claude, or both
Slash command
/voicemode:voicemode-connectThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Voice conversations through the voicemode.dev cloud platform. Connect your AI assistant to voice clients (iOS app, web app) without running local STT/TTS services.
Voice conversations through the voicemode.dev cloud platform. Connect your AI assistant to voice clients (iOS app, web app) without running local STT/TTS services.
Agents (Claude Code, claude.ai) connect via MCP to voicemode.dev. Clients (iOS app, web app) connect via WebSocket. The platform routes voice messages between them.
Add to your Claude Code MCP settings (~/.claude/settings.json):
{
"mcpServers": {
"voicemode-dev": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://voicemode.dev/mcp"]
}
}
}
When you first use a Connect tool, Claude Code will prompt for OAuth authentication. Sign in with your voicemode.dev account.
Open the iOS app or web dashboard (voicemode.dev/dashboard) and sign in with the same account.
Use the status tool to see connected devices, then use converse to have a voice conversation.
| Tool | Description |
|---|---|
status | Show connected devices and agents |
converse | Two-way voice conversation via connected client |
| Feature | Local VoiceMode | VoiceMode Connect |
|---|---|---|
| STT/TTS | Local (Whisper/Kokoro) | Client device (phone/browser) |
| Setup | Install services | Just add MCP server |
| Internet | Optional | Required |
| Latency | Lower | Higher |
| Mobile voice | No | Yes |
Use both: Local VoiceMode for desktop voice, Connect for mobile voice.
converse?These are documented in docs/connect/ as we learn more.
npx claudepluginhub mbailey/voicemode --plugin voicemodeEnables voice conversations with Claude Code using speech-to-text and text-to-speech. Includes setup, diagnostics, and MCP-based voice interaction.
Installs and configures VoiceMode MCP server for voice interactions in Claude Code using local Kokoro TTS and Whisper STT, with bash commands for uvx install, MCP addition, and endpoint config.
Builds ElevenLabs conversational AI voice agents: configure via CLI/dashboard, add tools/knowledge, integrate React/React Native/Swift/JS SDKs, test/deploy. For voice AI, phone systems, or ElevenLabs errors.