← Back to Skills Marketplace
TinkerClaw Jarvis Voice
by
Oscar Serra
· GitHub ↗
· v2.2.2
· MIT-0
5015
Downloads
3
Stars
32
Active Installs
12
Versions
Install in OpenClaw
/install jarvis-voice
Description
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum.
Usage Guidance
Install only if you want an always-on JARVIS-style voice/persona and are comfortable with your agent running a local `jarvis` command during replies. Review the actual `~/.local/bin/jarvis` script before use, confirm what it sends to `chat.inject`, and make sure you know how to disable the copied workspace templates or mute file if the voice behavior becomes unwanted.
Capability Assessment
Purpose & Capability
The stated purpose is JARVIS-style voice and humor, and local TTS is purpose-aligned; however the artifacts require the agent to run `jarvis` in the background for substantive replies and rely on that external helper to speak and post UI chat bubbles via `chat.inject`.
Instruction Scope
The templates make voice output mandatory for every reply or substantive reply, tell the agent to call `jarvis` automatically, and instruct workspace auto-loading so the behavior begins from the first reply of every session. This is broader than a simple optional persona style.
Install Mechanism
The declared install downloads a TTS model from GitHub and requires `ffmpeg`, `aplay`, `SHERPA_ONNX_TTS_DIR`, and a separate `~/.local/bin/jarvis` script. The artifact describes but does not include the actual script, so the main executable behavior cannot be fully verified from the package.
Credentials
Local audio playback, channel checks using `TC_SESSION_KEY`, a mute file under `~/.openclaw/data`, memory/session reads for greetings, and chat injection are related to the experience but create persistent host and UI side effects that need explicit user control.
Persistence & Privilege
No credential theft, privilege escalation, destructive behavior, or external exfiltration is evident. The persistence is mainly through copied workspace templates and a mute-state file, but those templates continuously steer future agent sessions.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install jarvis-voice - After installation, invoke the skill by name or use
/jarvis-voice - Provide required inputs per the skill's parameter spec and get structured output
Version History
v2.2.2
TinkerClaw rebrand + funnel to github.com/globalcaos/tinkerclaw
v2.2.1
Rename fork refs → tinkerclaw
v3.1.1
v3.1.1: Updated description — voice and humor are one package, like the original JARVIS. Added link to LIMBIC humor research paper.
v3.1.0
v3.1.0: Added HUMOR.md template — four humor patterns (dry wit, self-aware AI, alien observer, literal idiom) at maximum frequency. Jarvis Voice now ships voice + personality as one package. Copy templates/HUMOR.md to workspace root alongside VOICE.md and SESSION.md for the complete JARVIS experience.
v3.0.0
v3.0.0: Added VOICE.md and SESSION.md templates for workspace injection — voice is enforced from first reply of every session. Included portable jarvis script in bin/. Templates enforce: exec(jarvis, background:true) fires before text, bold Jarvis: prefix for transcript, never use tts tool. Lesson learned: without VOICE.md in workspace root, models forget voice instructions mid-session.
v2.3.0
New marketing copy: Iron Man/Stark hook, butler personality angle, Full JARVIS Experience section pairing with ai-humor-ultimate, and conversion link to GitHub fork.
v2.2.0
Security scan fixes: added metadata.openclaw block declaring required bins (ffmpeg, aplay), env (SHERPA_ONNX_TTS_DIR), skill dependency (sherpa-onnx-tts), install spec for Alan voice model download, and security notes explaining the exec pattern. Fixed version mismatch in _meta.json.
v2.1.0
Added webchat purple styling documentation: CSS class .jarvis-voice, markdown.ts auto-wrap hook, and cross-surface behavior notes.
v2.0.0
Complete rewrite: actionable instructions replacing marketing blurb. Documents hybrid output pattern (transcript + audio), explicit warning against tts tool, full command reference, ffmpeg effects chain, WhatsApp voice note format, installation guide with script.
v1.0.2
Fix repository/homepage links to fork
v1.0.1
SEO-optimized description and keywords for better discoverability
v1.0.0
v1.0.0: Metallic AI voice persona with sherpa-onnx TTS. JARVIS-like robotic voice effects.
Metadata
Frequently Asked Questions
What is TinkerClaw Jarvis Voice?
Turn your AI into JARVIS. Voice, wit, and personality — the complete package. Humor cranked to maximum. It is an AI Agent Skill for Claude Code / OpenClaw, with 5015 downloads so far.
How do I install TinkerClaw Jarvis Voice?
Run "/install jarvis-voice" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is TinkerClaw Jarvis Voice free?
Yes, TinkerClaw Jarvis Voice is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does TinkerClaw Jarvis Voice support?
TinkerClaw Jarvis Voice is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux).
Who created TinkerClaw Jarvis Voice?
It is built and maintained by Oscar Serra (@globalcaos); the current version is v2.2.2.
More Skills