Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From voicemode
Starts an ongoing voice conversation via the voicemode:converse MCP tool, with optional voice selection and initial message.
npx claudepluginhub mbailey/voicemode --plugin voicemodeHow this skill is triggered — by the user, by Claude, or both
Slash command
/voicemode:converseThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Start an ongoing voice conversation with the user using the `voicemode:converse` MCP tool.
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.
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.
Helps build low-latency voice agents using speech-to-speech (OpenAI Realtime) or pipeline (STT→LLM→TTS) architectures. Covers VAD, interruption handling, and tooling like Pipecat, Deepgram, ElevenLabs.
Share bugs, ideas, or general feedback.
Start an ongoing voice conversation with the user using the voicemode:converse MCP tool.
Call the voicemode:converse MCP tool. Argument handling:
$1 — optional voice name (e.g. af_river, samantha, nova). If non-empty, pass it as the voice parameter to the tool. If empty, omit voice so the tool uses its default.$2 — optional initial message. If non-empty, use it as the message to speak. If empty, let the tool / Claude choose an appropriate opener.All other parameters have sensible defaults.
/voicemode:converse — no args, default voice, Claude chooses opener/voicemode:converse af_river — use voice af_river, Claude chooses opener/voicemode:converse af_river "let's plan the day" — use voice af_river, open with the given messageIf $1 is provided but doesn't look like a known voice name (e.g. it contains spaces or punctuation that voices don't have), assume the user meant it as a message and pass it as the message instead — don't fail silently on a typo.
If the MCP server isn't connected or the tool isn't available:
Run the install command:
/voicemode:install
This installs VoiceMode CLI, FFmpeg, and local voice services.
Or install manually via CLI:
uvx voice-mode-install --yes
voicemode whisper service install
voicemode kokoro install
Check service status:
voicemode whisper service status
voicemode kokoro status
Reconnect MCP server after install:
Run /mcp, select voicemode, click "Reconnect" (or restart Claude Code)
For complete documentation, load the voicemode skill.