Read Aloud Plugin

The Read Aloud plugin adds a read aloud action on each assistant message. Clicking it sends the finished message to the shared speech (text-to-speech) service and plays the audio in the browser. It is play-on-demand, not a real-time voice conversation.

Configuration

plugins:
  - module: codumentor.plugins.read_aloud
    class: ReadAloudPlugin
    # args:
    #   enabled: true   # (default)

Parameter	Type	Default	Description
enabled	bool	true	Whether the action is shown.

The plugin has no other settings of its own. It uses the top-level shared speech: block (the same one Voice Mode and Telegram voice replies use):

speech:
  enabled: true
  base_url: "https://api.openai.com/v1"
  api_key: "${OPENAI_API_KEY}"
  tts_model: "tts-1"
  tts_voice: "alloy"

If speech is off, or base_url / api_key do not resolve, the action is shown disabled with an explanation.

What users see

• A read-aloud control on the final assistant message (never intermediate tool-call narration).
• One message plays at a time; starting another stops the previous one.

Notes

• Requirements: speech.enabled: true and an api_key that resolves to a real value via an environment variable. A per-user ${secret:…} key cannot resolve for this call (it runs outside an agent turn), so the action stays disabled in that case.
• Changes to the speech: block affect read-aloud, Voice Mode, and Telegram voice together.
• For a hands-free conversation (listen, talk, steer mid-task), see Voice Mode.