Claude Code Voice Hooks
Add audible feedback to Claude Code hook events so session and tool activity is easier to notice.
- Source repo
- shanraisshan/claude-code-hooks
- Stars
- ★ 560
- Last updated
- 4mo ago
- License
- MIT
- Primary language
- HTML
- FA score
- 34/100 · Major gaps
At a glance
- How it runs
- Works with
- Platform-specificClaude Code
- Cost
- Free, no paid service needed
- Setup effort
- Medium · a few setup steps
- You'll need
- Typical use
- A Claude Code user wants an audible cue when a session starts.
- Not a fit if
- Developers who do not use Claude Code
- Source review
- 34/100 · Major gaps 4 safety controls not found
What does this agent do, and when should you use it?
This repository configures sound feedback for Claude Code hooks and says it supports 30 hook events. It plays sounds for activity such as session starts, tool use, and agent responses. The README links to separate installation instructions for macOS, Linux, and Windows, and says the relevant prerequisites must be followed. To try it after installation, start claude in a terminal and send a prompt. The supplied material does not specify the audio runtime, installation commands, configuration details, or the sound mapped to each event.
Install and configure the repository's Claude Code hooks; after Claude Code starts, hook events such as sessions, tool use, and other activity trigger sounds. The README's quickstart is to run claude and send a prompt such as Hi. The repository also provides a hook event overview, a /workflows:workflow-changelog workflow to scan for new hooks and drift across files, and /workflows:workflow-add-hook <HookName> to add a recommended hook.
- A Claude Code user wants an audible cue when a session starts.
- A developer working on a coding task wants to notice tool use and agent responses through sound.
- A user wants to review which Claude Code hook events the repository covers.
- A maintainer wants to scan files for newly added hooks and drift with
/workflows:workflow-changelog. - A maintainer wants to add a recommended hook with
/workflows:workflow-add-hook <HookName>.
How do you install or deploy this agent?
The repository links to separate installation instructions for macOS, Linux, and Windows. Their contents are not included in the supplied material, so an exact install command and prerequisite list cannot be stated here. Follow the instructions for your operating system and complete their prerequisites; the README says missing prerequisites may cause SessionStart:startup hook error when Claude Code starts.
How do you use this agent?
After installing and meeting the prerequisites for your operating system, start Claude Code in a terminal:
claudeSend a prompt, for example Hi. The README says session starts, tool use, agent responses, and more will produce sound.
What are this agent's strengths and limitations?
- The README reports support for 30 Claude Code hook events, including session and tool activity.
- Installation instructions are linked for macOS, Linux, and Windows.
- Includes workflows for scanning hook changes across files and adding a named hook.
- It is specifically documented for Claude Code; the supplied material shows no path for other coding agents or platforms.
- The supplied material does not include exact install commands, prerequisites, or audio runtime requirements.
- The README warns that missing prerequisites can cause
SessionStart:startup hook errorat startup. - It does not explain whether sounds can be customized, which sounds are assigned by default, or how to disable them.
How does this agent compare with similar options?
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Claude Code Voice Hooks This agent | 34 · Major gaps | Agent plugin / skillFree | ★ 560 | 4mo ago | HTML | Claude Code |
| Harmonist | 78 · Good | CLIFree + model costs | ★ 2.3k | 4mo ago | Python | — |
| dmux | 69 · Some gaps | CLIFree + model costs | ★ 1.8k | 2mo ago | HTML | Codex · Claude Code · OpenAI API |
| Vibe Coding Toolkit | 66 · Some gaps | Agent plugin / skillFree | ★ 1.7k | today | JavaScript | — |
How does FollowAgents rate this agent?
Why each dimension lost points
The README describes voice feedback through Claude Code hooks and links to installation notes for macOS, Linux, and Windows, giving some indication of purpose and possible system effects. The supplied material contains no hook implementation, permission scope, confirmation mechanism, data handling details, sensitive-data safeguards, dependency list, or rollback steps. The developer attribution is a limited source clue, but publisher identity is unverified and maintenance responsibility is unclear, so scores reflect only visible evidence.
The README lists hook counts, versions, and dated additions, and says missing prerequisites may cause a startup error. These provide limited consistency and failure information, but no implementation, dependency versions, or detailed diagnostics are supplied, limiting verification of the claims and dependency availability.
The README identifies Claude Code users as the audience, provides installation links for three operating systems, and claims broad hook coverage. It gives little detail about scenarios, capability boundaries, trigger behavior, or environment requirements; those would require the omitted installation and hook files to assess.
The README provides installation links, demos, other references, and a dated list of hook changes. The LICENSE clearly identifies MIT and includes its terms. Installation detail, error guidance, and known limitations are sparse; naming and maintenance responsibility are also unclear, and the changelog focuses on hook additions.
The stated purpose—playing sounds on hooks—is clear and could provide immediate audio feedback during Claude Code sessions if implemented as described. The supplied material does not show actual outputs, configuration options, resource costs, or comparative benefits, so usefulness and cost are only partly supported.
The README links some version changes to Claude Code release information and points to hook documentation and demos, providing limited traceability. Only the README and LICENSE are supplied, with no implementation or independent corroboration, and the materials do not show whether claims are separated from inference.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: sensitive-data handlingUse dedicated, low-privilege, revocable API keys — never production credentials — and keep secrets out of logs.
- Not found in source: dependency securityPin versions and run a dependency audit (npm audit, pip-audit) before installing; prefer running it in a container.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- This assessment uses only the supplied README and LICENSE; installation details, hook implementations, dependencies, and configuration were not provided for review.
- The README mentions a startup hook error when prerequisites are unmet, but the supplied material does not provide complete diagnosis or recovery steps.
FAQ
Which operating systems are covered?
How can I quickly check that the sound hooks work?
claude and send Hi. The README says session starts, tool use, and agent responses can trigger sounds.