agentleFS
Sign inStart free
HyperfocuSamHyperfocuSam/claude-voice/skills/voice-mode/SKILL.md

voice-mode

Skill0 starsChanged 8 months agoMITView on GitHub

Speak Claude Code responses aloud using text-to-speech. Use when the user says "voice mode", "voice mode on", "speak this", "read this out", "read that aloud", or "voice mode for the above". Supports macOS say (default), OpenAI TTS, and MiniMax TTS providers.

  • Reads credentials

3 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions3 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 3

    1. eliasstravik/skills★ 22same name
    2. idanbeck/claude-skills★ 14same name
    3. ryangalea23/claude-skills★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Remove code blocks -> "I've included a code block here."

    line 32
  2. Distinctive:

    Remove backticks, keep the text inside.

    line 33
  3. Distinctive:

    Keep under 5000 characters, truncating at a sentence boundary.

    line 39
  4. Distinctive:

    Run the speak script:

    line 40
  5. Distinctive:

    If the TTS fails, inform the user and continue text-only.

    line 68

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Voice Mode

Speak Claude Code responses aloud via text-to-speech.

Activation

  • On: "voice mode", "voice mode on", "voice mode start"
  • Off: "voice mode off", "stop voice mode", "voice off"
  • One-shot: "speak this", "read this out", "voice mode for the above"

How to enable persistent voice mode

mkdir -p ~/.claude-voice && touch ~/.claude-voice/enabled

This creates the flag file that the Stop hook checks. When enabled, every response is automatically spoken aloud when the conversation ends.

How to speak a response (one-shot)

  1. Take your most recent response text.
  2. Adapt it for speech:
    • Remove code blocks -> "I've included a code block here."
    • Remove backticks, keep the text inside.
    • Convert ## Headers -> "Section: [title]."
    • Convert bullet lists -> "First: ... Next: ... Also: ..."
    • Strip URLs, keep link text.
    • Replace tables -> "Here's a table with N rows."
    • Strip bold/italic markers.
    • Keep under 5000 characters, truncating at a sentence boundary.
  3. Run the speak script:
python3 ${CLAUDE_PLUGIN_ROOT}/scripts/speak.py "Adapted text here"

Configuration

Users configure their provider in ~/.claude-voice/config.yaml:

provider: say          # say | openai | minimax

The speak script reads this automatically. No need to pass --provider unless overriding.

Provider options

ProviderSetupFlags
sayNone (macOS default)--voice Samantha
openaiOPENAI_API_KEY--voice nova
minimaxMINIMAX_API_KEY--emotion happy

Limits

  • Max 5000 characters per call (adapt_text truncates automatically).
  • For very long responses, the text is truncated at a sentence boundary.
  • If the TTS fails, inform the user and continue text-only. Do not retry more than once.

Disabling

rm ~/.claude-voice/enabled

Or use the /voice off command.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free