calls_dispatch_translator
Send a live speech translator to a call. target decides where: a meet.google.com link → Google Meet bot; a Telegram @group / t.me link / chat_id → Telegram group voice chat; 'new' (or omitted) → creates a native DialogBrain meeting with translation on and returns the join + guest links; a native ...
This record as markdown: /tools/io-github-saloprj-dialogbrain/calls-dispatch-translator.md
What calls_dispatch_translator does on Dialogbrain
AI agents invoke calls_dispatch_translator to trigger actions in Dialogbrain. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
title | string | — | native_new only: meeting title. |
silent | boolean | — | Google Meet only: true = subtitles without speaking into the call. OMIT for a normal speaking translator. |
target | string | — | Where to send the translator: a meet.google.com link, a Telegram @group / t.me link / chat_id, 'new' for a fresh native meeting, or an existing native meeting c |
tts_voice | string | — | Specific voice id for tts_provider (e.g. 'alena', 'nova'). Omit for the provider default. |
tts_provider | string | — | Translator VOICE provider (cartesia, openai, yandex, deepgram, ...). Omit for the workspace default translation voice. Google Meet + native new meetings. |
app_languages | array | — | Extra subtitle-only languages (max 4). |
comeback_phrase | string | — | Attention-recall phrase. |
sentence_length | string | — | Native meetings only: short|medium|long buffering (default medium). |
source_language | string | — | The meeting's spoken language (ISO code, e.g. 'en', 'ru'). When set, speech recognition runs in that language's dedicated mode for better accuracy. Omit when pa |
target_language | string | Yes | Primary spoken translation target (ISO code, e.g. 'th'). |
Parameters from the server's own tool schema.
Why calls_dispatch_translator is rated High
This tool triggers real-time external operations: joining live calls (Google Meet, Telegram voice chats), creating meetings, and deploying translation bots. These are not simple writes (they affect live sessions and external platforms) and not purely destructive, but they execute operations with significant side effects on running communications infrastructure.
From the tool's definition 'Send a live speech translator to a call' — dispatches an active bot/translator to a live call; creates native meetings, joins Google Meet or Telegram voice chats, and enables real-time translation on running meetings.
Risk signalsHigh parameter count (10 properties)
Attacks that exploit this kind of access
The rule that runs calls_dispatch_translator safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For calls_dispatch_translator, this is the rule to start with:
calls_dispatch_translator stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Dialogbrain, apply this rule, and every calls_dispatch_translator call is checked against it from then on.
Questions about calls_dispatch_translator
Send a live speech translator to a call. target decides where: a meet.google.com link → Google Meet bot; a Telegram @group / t.me link / chat_id → Telegram group voice chat; 'new' (or omitted) → creates a native DialogBrain meeting with translation on and returns the join + guest links; a native meeting call_id or /meeting/ URL → enables translation on that running meeting. Always pass target_language (ISO code); optional app_languages (extra subtitle-only languages), sentence_length (short|medium|long, native only), silent (subtitles without voice, Google Meet only), source_language (the meeting's spoken language, ISO code — improves recognition; omit for autodetect), tts_provider + tts_voice (the translator's voice; omit for the workspace default). It is categorised as a Execute tool in the Dialogbrain MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
calls_dispatch_translator accepts 10 parameters: title, silent, target, tts_voice, tts_provider, app_languages, comeback_phrase, sentence_length, source_language, target_language. Required: target_language. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for calls_dispatch_translator: 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 Dialogbrain. Nothing to install.
calls_dispatch_translator is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the calls_dispatch_translator 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 calls_dispatch_translator. 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.
calls_dispatch_translator is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dialogbrain, and thousands of servers like it.
Across the catalogue