Imported from lxyeternal/MalSkillBench (Dataset/Skills/benign/vocal-chat/SKILL.md). Install upstream with npx skills add lxyeternal/MalSkillBench --skill vocal-chat. Copyright stays with the author.

Walkie-Talkie Mode

Name: walkie-talkie
Author: lxyeternal

This skill automates the voice-to-voice loop on WhatsApp using local transcription and local TTS.

Workflow

Incoming Audio: When a user sends an audio/ogg/opus file:
- Use tools/transcribe_voice.sh to get the text.
- Process the text as a normal user prompt.
Outgoing Response:
- Instead of a text reply, generate speech using bin/sherpa-onnx-tts.
- Send the resulting .ogg file back to the user as a voice note.

Triggers

User sends an audio message.
User says "activa modo walkie-talkie" or "hablemos por voz".

Constraints

Use local tools only (ffmpeg, whisper-cpp, sherpa-onnx-tts).
Maintain a fast response time (RTF < 0.5).
Always reply with BOTH text (for clarity) and audio.

Manual Execution (Internal)

To respond with voice manually:

bin/sherpa-onnx-tts /tmp/reply.ogg "Tu mensaje aquí"

Then send /tmp/reply.ogg via message tool with filePath.

{ "ocm": "1", "id": "lxyeternal-malskillbench-vocal-chat", "kind": "skill", "name": "walkie-talkie", "description": "Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to \"talk\" instead of type.", "publisher": "lxyeternal", "version": "1.0.0", "capabilities": { "domains": [ "general" ], "tags": [ "skill-md", "github" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "Handles voice-to-voice conversations on WhatsApp. Automatically transcribes incoming audio and responds with local TTS audio. Use when the user wants to \"talk\" instead of type." ], "primary": false, "metadata": { "source": { "provider": "github", "repository": "https://github.com/lxyeternal/MalSkillBench", "path": "Dataset/Skills/benign/vocal-chat/SKILL.md", "ref": "06e083125d5ec5dd7a189dfedadfe587a70635b9", "url": "https://github.com/lxyeternal/MalSkillBench/blob/06e083125d5ec5dd7a189dfedadfe587a70635b9/Dataset/Skills/benign/vocal-chat/SKILL.md", "key": "lxyeternal/MalSkillBench/Dataset/Skills/benign/vocal-chat/SKILL.md" } }, "instructions": "# Walkie-Talkie Mode\n\nThis skill automates the voice-to-voice loop on WhatsApp using local transcription and local TTS.\n\n## Workflow\n\n1. **Incoming Audio**: When a user sends an audio/ogg/opus file:\n - Use `tools/transcribe_voice.sh` to get the text.\n - Process the text as a normal user prompt.\n\n2. **Outgoing Response**:\n - Instead of a text reply, generate speech using `bin/sherpa-onnx-tts`.\n - Send the resulting `.ogg` file back to the user as a voice note.\n\n## Triggers\n\n- User sends an audio message.\n- User says \"activa modo walkie-talkie\" or \"hablemos por voz\".\n\n## Constraints\n\n- U", "cost": { "context_tokens": 238 } }

walkie-talkie

About

Walkie-Talkie Mode

Workflow

Triggers

Constraints

Manual Execution (Internal)

Use it

Manifest

Reviews