generate_audio
Generate speech (text-to-speech) for the title. Billed per character. The voice comes from the tier's model unless you pass one in params. Runs as a job: the call waits up to about two minutes and returns the result; if it is not ready by then it returns the generation with status queued/running ...
This record as markdown: /tools/com-idosgames-platform/generate-audio.md
What generate_audio does on iDos Games
AI agents use generate_audio to create or update resources in iDos Games, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your iDos Games environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | The words to say out loud. They are read verbatim, so do not put instructions here. |
tier | string | — | Quality/price tier, e.g. image-cheap or video-premium. Call list_ai_tiers for the current list. Omit it to use this title's default tier. |
model | string | — | Model name, if you insist on a specific one (optional). ⚠ Setting it cancels the tier COMPLETELY — together with its provider and its settings — so params may s |
params | object | — | Model settings, as declared by the vendor for the chosen tier — for example {"aspect_ratio":"16:9","resolution":"720p","duration":"4"}. Call list_ai_tiers to se |
provider | string | — | Provider key, if you insist on one (optional). Cancels the tier the same way. |
title_id | string | — | Which game this is for — a label for the report, optional. Credits are always the publisher's, so leaving it out is normal for assets that belong to no game. |
Parameters from the server's own tool schema.
Why generate_audio is rated Medium
An AI agent can call generate_audio faster than any human can review: one bad instruction and it creates or modifies resources in iDos Games by the hundred, each call as confident as the last.
Attacks that exploit this kind of access
The rule that runs generate_audio safely
PolicyLayer is an MCP gateway: it sits between your AI agents and iDos Games, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For generate_audio, this is the rule to start with:
generate_audio stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect iDos Games, apply this rule, and every generate_audio call is checked against it from then on.
Questions about generate_audio
Generate speech (text-to-speech) for the title. Billed per character. The voice comes from the tier's model unless you pass one in params. Runs as a job: the call waits up to about two minutes and returns the result; if it is not ready by then it returns the generation with status queued/running — poll get_generation with its id. It is categorised as a Write tool in the iDos Games MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
generate_audio accepts 6 parameters: text, tier, model, params, provider, title_id. Required: text. The full parameter table on this page comes from the server's own tool schema.
Register the iDos Games MCP server in PolicyLayer and add a rule for generate_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 iDos Games. Nothing to install.
generate_audio is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_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 generate_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.
generate_audio is provided by the iDos Games MCP server (https://site.idosgames.com/api/v2/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on iDos Games, and thousands of servers like it.
This server
Across the catalogue