Vocal Chat

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.

Before installing or enabling this skill, verify the following: (1) Confirm which binaries and scripts it requires (ffmpeg, whisper-cpp, sherpa-onnx-tts, tools/transcribe_voice.sh, bin/sherpa-onnx-tts) and install them from trusted sources — the manifest currently lists none. (2) Ensure your agent actually has a 'message' tool and WhatsApp integration set up and understand what credentials or API access that requires; the skill does not declare any credentials. (3) Ask the publisher to update the manifest to list required binaries, install instructions, and any needed credentials. (4) Consider running the skill in a sandbox or test account first — audio processing can involve sensitive content, and the skill assumes local filesystem access which could fail or be abused. (5) Note the performance constraint (RTF < 0.5) may be unrealistic for local models and could lead to degraded behavior; confirm resource needs. If the publisher cannot clarify these gaps, treat the skill as untrusted.

Type: OpenClaw Skill Name: vocal-chat Version: 1.0.0 The skill bundle describes a 'walkie-talkie' mode for an AI agent, enabling voice-to-voice conversations using local transcription and text-to-speech. The `SKILL.md` clearly outlines the workflow, triggers, and constraints, explicitly stating the use of 'local tools only' (ffmpeg, whisper-cpp, sherpa-onnx-tts). There is no evidence of intentional harmful behavior such as data exfiltration, malicious execution, persistence, or prompt injection attempts against the agent from the skill's instructions themselves. The instructions are aligned with the stated purpose and do not exhibit high-risk behaviors.