WA MCP

transcribe_voice_note

Read-only

Transcribes WhatsApp voice notes (and other audio messages) into text, in the language spoken, so you can read, quote or summarize them. Works in any chat, groups and forwarded notes included. Paid plan only: on the free plan the call is refused with a note on how to subscribe. Pass up to 10 message ids at once (e.g. every "[voice note, …]" of a chat from read_chat_history or search_messages). Each note is transcribed once and saved: asking again returns the saved text, and read_chat_history and search_messages then show it in place of the note ("[voice note, 0:42, transcribed] "…""). Notes over 10 minutes or very large audio files can't be transcribed, and each account has a monthly allowance of audio minutes (the result shows what's used). Many notes can take a while: the tool answers within about 45 seconds, and notes not done by then come back as "processing" and keep going on the server; call again with those ids in a minute or two to get them. Returns { results: [{ message_id, status (transcribed, processing, no_speech, too_short, too_long, too_large, expired, failed, not_audio, not_found, monthly_limit, retry_later), text?, language?, duration?, note? }], month }.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "message_ids": "<message_ids>"
    },
    "name": "transcribe_voice_note"
  }
}

Input Schema

Name	Required	Description	Default
`message_ids`	Yes	The ids of the voice notes to transcribe (1 to 10), as read_chat_history or search_messages show them.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 12, 2026

TDQS

A4.8/5.0

Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Far exceeds what readOnlyHint/openWorldHint convey: it discloses paywall gating, idempotent caching ('Each note is transcribed once and saved', repeat calls return saved text), an account-level monthly minute allowance, a ~45 second response ceiling with 'processing' polling guidance, and per-size/duration failure modes. It even explains the visible side effect on sibling tools' output ('[voice note, 0:42, transcribed] "…"'), which is exactly the kind of cross-tool consequence annotations cannot express.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with purpose and benefit, then prerequisites, batching, failure modes, latency, and return shape in a logical order with no filler sentences. It is dense and the final return-value sentence is long, but every clause carries operational information an agent needs before calling.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the return contract and does so thoroughly, enumerating all status values and optional fields (text, language, duration, note) plus the top-level month field. Combined with limits, latency, and polling guidance, nothing material is missing for a single-parameter batch tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single parameter already documents the 1-10 range and id source, so the baseline is 3. The description adds value by showing the actual id-bearing marker format ('every "[voice note, …]"') an agent should collect, making batch construction concrete rather than abstract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource ('Transcribes WhatsApp voice notes ... into text') and immediately states the agent-facing benefit (read, quote, summarize). It also positions itself relative to siblings by naming read_chat_history and search_messages as the sources of message ids, so an agent can route between them without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit prerequisites (paid plan only; free-plan calls are refused with a subscribe note), a batching rule ('Pass up to 10 message ids at once'), and a concrete acquisition path for ids from read_chat_history or search_messages. It also states exclusion conditions (notes over 10 minutes, very large files) and the retry protocol for slow notes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All WA MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.