Lovefromio Jarvis Voice
by @lovefromio
Metallic AI voice persona with TTS and visual transcript styling. Speak responses aloud with a JARVIS-like robotic voice and display transcripts in purple it...
clawhub install lovefromio-jarvis-voiceπ About This Skill
name: jarvis-voice version: 1.0.0 description: Metallic AI voice persona with TTS and visual transcript styling. Speak responses aloud with a JARVIS-like robotic voice and display transcripts in purple italics. homepage: https://github.com/openclaw/openclaw repository: https://github.com/openclaw/openclaw metadata: openclaw: emoji: "ποΈ" requires: bins: ["ffmpeg", "aplay"] install: - id: sherpa-onnx kind: manual label: "Install sherpa-onnx TTS (see docs)"
Jarvis Voice Persona
A metallic AI voice with visual transcript styling for OpenClaw assistants.
Features
Requirements
sherpa-onnx with VITS piper model (en_GB-alan-medium recommended)ffmpeg for audio processingaplay (ALSA) for audio playbackInstallation
1. Install sherpa-onnx TTS
# Download and extract sherpa-onnx
mkdir -p ~/.openclaw/tools/sherpa-onnx-tts
cd ~/.openclaw/tools/sherpa-onnx-tts
Follow sherpa-onnx installation guide
2. Install the jarvis script
cp {baseDir}/scripts/jarvis ~/.local/bin/jarvis
chmod +x ~/.local/bin/jarvis
3. Configure audio device
Edit ~/.local/bin/jarvis and set your audio output device in the aplay -D line.
Usage
Speak text
jarvis "Hello, I am your AI assistant."
In agent responses
Add to your SOUL.md:
## Communication ProtocolHybrid Output: Every response includes text + spoken audio via jarvis command
Transcript Format: Jarvis: spoken text
No gibberish: Never spell out IDs or hashes when speaking
Transcript styling (requires UI support)
Add to your webchat CSS:
.jarvis-voice {
color: #9B59B6;
font-style: italic;
}
And allow span in markdown sanitization.
Voice Customization
Edit ~/.local/bin/jarvis to adjust:
| Parameter | Effect |
|-----------|--------|
| --vits-length-scale=0.5 | Speed (lower = faster) |
| aecho delays | Metallic resonance |
| chorus | Thickness/detuning |
| highpass/lowpass | Frequency range |
| treble=g=3 | Metallic sheen |
Presets
More robotic:
aecho=0.7:0.7:5|10|15:0.4|0.35|0.3
More human:
aecho=0.4:0.4:20:0.2
Deeper:
highpass=f=200,lowpass=f=3000
Troubleshooting
No audio output
aplay -l for available devices-D plughw:X,Y parameterVoice too fast/slow
--vits-length-scale (0.3=very fast, 1.0=normal)Metallic effect too strong
Files
scripts/jarvis β TTS script with metallic processingSKILL.md β This documentation*A voice persona for assistants who prefer to be heard as well as read.*
π‘ Examples
Speak text
jarvis "Hello, I am your AI assistant."
In agent responses
Add to your SOUL.md:
```markdown
π Tips & Best Practices
No audio output
aplay -l for available devices-D plughw:X,Y parameterVoice too fast/slow
--vits-length-scale (0.3=very fast, 1.0=normal)