Walkie Talkie 2
Apps & Automationwalkie-talkie-2Walkie Talkie 2 is an Agent Skill for apps & automation published in the sundial-org/awesome-openclaw-skills repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
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.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/sundial-org/awesome-openclaw-skills/blob/HEAD/skills/walkie-talkie-2/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/walkie-talkie-2, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Walkie-Talkie Mode
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.shto get the text. - Process the text as a normal user prompt.
- Use
-
Outgoing Response:
- Instead of a text reply, generate speech using
bin/sherpa-onnx-tts. - Send the resulting
.oggfile back to the user as a voice note.
- Instead of a text reply, generate speech using
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.