How to make Claude Code talk: every text-to-speech option compared.

(1)say hook

The two-minute version: pipe the last message into say.

The Stop hook receives JSON on stdin that includes last_assistant_message. Extract it with jq and hand it to say. "async": true keeps Claude Code from waiting on the speech, and head -c stops a long reply from talking for minutes.

It costs nothing and needs no install beyond jq. The catch is that it reads Markdown, file paths and code exactly as written, which is hard to follow by ear.

{
  "hooks": {
    "Stop": [
      {
        "hooks": [
          {
            "type": "command",
            "command": "jq -r '.last_assistant_message // empty' | head -c 600 | say",
            "async": true
          }
        ]
      }
    ]
  }
}

(2)read-aloud plugins

claude-code-narrator and claude-code-tts read locally with Kokoro.

claude-code-narrator is a Claude Code plugin. It speaks short descriptions of tool use (“Reading file settings dot json”), the text between tool calls, the first thousand or so characters of the final reply, and notification text. It goes quiet when you type or click, uses the local Kokoro engine with eight voices, and runs on macOS and Linux.

claude-code-tts by Omnicapable speaks every reply from a Stop hook with local Kokoro ONNX (about a 336 MB model), skipping code blocks, tables, URLs and emoji. It supports macOS 12+ and Windows. A separate npm package of the same name defaults to Edge TTS, which is Microsoft’s online service, with Kokoro as the offline fallback.

/plugin marketplace add shreyas-s-rao/claude-code-narrator
/plugin install narrator
/reload-plugins
/narrator:on

(3)VoiceMode

VoiceMode, if you want to talk with Claude, not just listen.

VoiceMode is the most established option here, with about 1,400 GitHub stars and an MIT license. It is an MCP server and Claude Code plugin for back-and-forth voice conversations: Claude speaks, you answer out loud. It can run fully local with Whisper.cpp and Kokoro, or use OpenAI’s cloud. It works on macOS, Linux and Windows.

Pick VoiceMode when the goal is a spoken conversation with one session, or when you are not on a Mac. It is built for talking with an agent, not for keeping track of several agents at once.

claude plugin marketplace add mbailey/voicemode
claude plugin install voicemode@voicemode
/voicemode:install

(4)Heard

Heard summarizes instead of reading, across every session.

Heard installs Claude Code hooks and decides what deserves speech: questions, approvals, failures and results get through, while routine tool churn gets a one-liner or stays quiet. With several sessions running, each update starts with the project name. Three listening modes set how much you hear, from short signposts to alerts only.

The open-source engine is free under Apache 2.0, with local Kokoro voices and no account. The Mac app adds managed voices and, on Power, voice replies and Parrot recaps. Heard is macOS only.

git clone https://github.com/heardlabs/heard.git && cd heard
python3 -m venv .venv && source .venv/bin/activate && pip install -e .
heard install claude-code

(5)Choosing

Match the tool to what you want to hear.

All of these are honest choices. They answer different needs.

• Every word of the final reply, free: the say hook.
• A local narrator for one session on macOS or Linux: claude-code-narrator.
• Replies read aloud on Windows: claude-code-tts.
• A spoken back-and-forth conversation, on any OS: VoiceMode.
• Short spoken summaries across several Claude Code and Codex sessions on a Mac: Heard.