add-voice-transcription

To transcribe WhatsApp voice notes using OpenAI Whisper, you can use this skill to automatically convert incoming audio messages into readable text. It injects the transcript into the agent context as [Voice: <transcript>] for bot reasoning.

Yes, you need an OpenAI API key to enable WhatsApp voice message transcription. The skill requires this key to integrate with OpenAI's Whisper API for processing audio and generating high-quality text transcripts.

Yes, you can use this voice transcription skill with existing WhatsApp channels. It is designed for NanoClaw deployments, allowing you to merge the skill into your workflow to turn audio into text for bot responses.

Automatic audio transcription for WhatsApp bots works by sending incoming voice notes to the Whisper API. The API converts the audio to text, which is then injected into the agent context so the bot can read and respond to the voice message.

The best way to convert WhatsApp audio to text for agent reasoning is using OpenAI Whisper. This skill automates the transcription process, securely passing the text transcript directly to the agent for processing and response generation.