Transcribe a WhatsApp voice message or audio to text. Server-side transcription via Speaches (Whisper). Optionally replies to the original message with the transcription text. Args: - contactId: Phone digits or
AI agents call whatsapp_transcribe_audio to retrieve information from Waha without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Transcribing audio is a retrieval and conversion operation that does not create, modify, delete, or destroy data. The optional reply feature is a secondary write action, but the primary function is data extraction (Read). No side effects occur to the audio message itself.
From the tool's definition Tool performs transcription of existing audio to text with 'Optionally replies' — core operation is reading/extracting data from a voice message without modification or deletion of the original.
Attacks that exploit this kind of access
Transcribe a WhatsApp voice message or audio to text. Server-side transcription via Speaches (Whisper). Optionally replies to the original message with the transcription text. Args: - contactId: Phone digits or. It is categorised as a Read tool in the Waha MCP Server, which means it retrieves data without modifying state.
Register the Waha MCP server in PolicyLayer and add a rule for whatsapp_transcribe_audio: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Waha. Nothing to install.
whatsapp_transcribe_audio is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the whatsapp_transcribe_audio rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for whatsapp_transcribe_audio. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
whatsapp_transcribe_audio is provided by the Waha MCP server (@marcos-heidemann/waha-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →