用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/mbailey/voicemode --skill converse命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
Voice interaction for Claude Code. Use when users mention voice mode, speak, talk, converse, voice status, or voice troubleshooting.
Add and use custom voices for VoiceMode TTS via local mlx-audio. Use when the user wants to clone a voice, do an impression, add a reference clip, or use voice="<name>" in converse.
Remote voice via VoiceMode Connect. Use when users want to add voice to Claude Code using their phone or web app, without local STT/TTS setup.
正在显示 SKILL.md
基于 SOC 职业分类
| name | converse |
| description | Start an ongoing voice conversation |
| argument-hint | [voice] [message] |
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.voice://voices MCP resource; to speak in character, first read the persona at ~/.voicemode/voices/<voice>/README.md (index: ~/.voicemode/voices/PERSONAS.md).All other parameters have sensible defaults.
Multi-agent turn-taking: in a session where more than one agent shares the voice channel, pass hold_conch=true when your next converse call will continue the thread (you're asking a question you'll answer, or speaking across several turns). It keeps the floor so other agents wait instead of cutting in at the turn boundary; the default false releases it after the exchange.
/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:
voicemode reconnect
One Bash call drives the whole /mcp reconnect dance on your own pane —
survives the drop because Bash and tmux stay up when the MCP tools vanish.
After it prints RESULT: reconnected, run the ToolSearch select:… line it
echoes to reload the tool schema, then resume conversing. (Manual fallback:
run /mcp, select voicemode, click "Reconnect", or restart Claude Code.)
Mid-session drop (voice was working, then -32000 Connection closed): you
don't need to reinstall — just run voicemode reconnect. See the voicemode
skill's "Reconnecting after a mid-session drop" section.
For complete documentation, load the voicemode skill.