home / skills / openclaw / skills / protoss-voice

protoss-voice skill

safe

This skill applies Protoss-style psionic effects to audio files, transforming raw recordings or TTS output into a layered, immersive final.

npx playbooks add skill openclaw/skills --skill protoss-voice

Review the files below or copy the command above to add this skill to your agents.

Files (3)

SKILL.md

2.0 KB

---
name: protoss-voice
description: Apply Protoss-style (StarCraft) psionic effects to ANY audio file. Use as a post-processing layer for TTS or user recordings.
metadata:
  openclaw:
    emoji: "🔮"
    requires:
      bins:
        - ffmpeg
        - sox
    install:
      - id: brew
        kind: brew
        formula: "sox ffmpeg"
        bins:
          - sox
          - ffmpeg
        label: "Install Dependencies (brew)"
---

# Protoss Voice Effect

Applies a "Khala" psionic transformation chain to audio files using the V9 "Massive Void" engine.
**Modular Design:** This skill does NOT generate speech. It transforms existing audio.

## Usage

Run the script on any input audio file (wav, mp3, ogg, etc):

```bash
python3 skills/protoss-voice/protoss_fx.py <path_to_audio_file>
```

**Output:**
Creates a new file with suffix `_psionic.wav` in the same directory.

## Agent Protocol & Behavior

When acting as a Protoss persona (e.g., Selendis, Artanis, Zeratul, etc), the agent should:

1.  **Generate/Record Base Audio:**
    *   Use `kokoro-tts` (or any other TTS skill) to generate the raw speech.
    *   OR accept a user-provided recording.
2.  **Process (The "Black Box"):**
    *   Execute `protoss_fx.py` on the raw file.
    *   *Do not narrate this step unless debugging.*
3.  **Deliver Final Artifact:**
    *   Send the **processed** file (`_psionic`) using the `message` tool.
    *   Clean up raw/intermediate files silently if they are temporary.

## Integration Example (Kokoro)

```bash
# 1. Generate (Raw)
python3 skills/kokoro-tts/speak.py "En Taro Adun." -o raw.wav -v ef_dora

# 2. Transform (Psionic)
python3 skills/protoss-voice/protoss_fx.py raw.wav
# Output: raw_psionic.wav

# 3. Optimize for Transport (Telegram OGG)
ffmpeg -i raw_psionic.wav -c:a libopus -b:a 64k -vbr on final.ogg -y

# 4. Send
message(action="send", media="final.ogg", asVoice=true)
```

## Requirements

Requires `ffmpeg` and `sox` (Sound eXchange).

```bash
brew install ffmpeg sox
```

Overview

This skill applies a Protoss-style psionic audio transformation to any existing audio file. It is a post-processing layer only — it does not generate speech. Use it to add alien, layered, and resonant psionic effects to TTS output or user recordings. Output files are written alongside the input with a _psionic suffix.

How this skill works

The script runs an audio processing chain (the V9 "Massive Void" engine) to apply filters, modulation, harmonics, and spatial psionic textures. It accepts common formats (wav, mp3, ogg) and produces a processed WAV file with a _psionic suffix. The tool relies on ffmpeg and sox for format handling and audio transformations. It is designed as a deterministic post-processing step that can be inserted into TTS or recording workflows.

When to use it

Enhance TTS output to sound like a Protoss/psionic persona.
Post-process actor or user voice recordings for sci-fi projects.
Create themed audio for games, podcasts, or voice lines.
Add layered resonance and otherworldly presence to narration.
Batch-process existing audio assets during sound design passes.

Best practices

Generate or record a clean dry source with low noise and consistent level before processing.
Use lossless or high-bitrate input (WAV) for best effect; avoid heavily compressed sources when possible.
Normalize levels before running the effect to prevent clipping during modulation stages.
Chain this skill after TTS or voice recording but before final encoding/compression.
Cleanup intermediate files if used in automated pipelines to save storage.

Example use cases

Turn kokoro-tts output into a Protoss-sounding line for a game character.
Process an actor’s recording to produce a mysterious commander voice for a sci-fi podcast.
Batch-convert voice assets for a mod or fan project to a unified psionic style.
Create short themed voice clips for chatbots or community events with an alien aesthetic.

FAQ

What formats are accepted as input?

Common audio formats such as WAV, MP3, and OGG are accepted; output is a WAV file with a _psionic suffix.

Do I need additional software installed?

Yes. ffmpeg and sox are required for format handling and processing. Install them via your system package manager or Homebrew on macOS.

Does this skill generate speech from text?

No. This skill only transforms existing audio. Use a TTS skill or a recorded file as the input.