Agent skill · creative production · sundial-org
walkie-talkie-2
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.
Why this skill is useful
Adds executable scripts for local transcription and TTS that enable voice interactions on WhatsApp, which the AI cannot generate on its own.
What it needs
Requires ffmpeg, sherpa-onnx-tts, whisper-cpp installed locally. About 1k tokens when loaded. Last updated 2026-03-07. 639 stars on the source repository.
What this skill does
Walkie-Talkie Mode This skill automates the voice-to-voice loop on WhatsApp using local transcription and local TTS. Workflow 1. Incoming Audio: When a user sends an audio/ogg/opus file: Use tools/transcribevoice.sh to get the text. Process the text as a normal user prompt. 2. 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: Then send /tmp/reply.ogg via message tool with filePath.
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills sundial-org/walkie-talkie-2