AI and media

AI agents that use ElevenLabs

UtilitySpaces gives an AI agent scoped access to ElevenLabs through its own encrypted connection, not your password. The agent can call 4 named ElevenLabs tools, and the one that writes waits for a person's approval unless an admin has set the connection to run without asking. Every call is written to a hash-chained audit log with its arguments and its result.

What an agent can do in ElevenLabs

Browse voices and models, check subscription usage, and synthesize speech with ElevenLabs. An agent calls these by name, and matching is exact.

Every tool a ElevenLabs connection exposes, and whether it writes, which waits for approval by default
Tool	What it does	Waits for approval by default
List voices	List voices available to this key, with their voice ids.	No — read only
Get subscription	Get the account's plan, character quota, and usage so far.	No — read only
Text to speech	Synthesize speech for a voice (billed call). Returns raw audio bytes, not JSON: the response comes back as an unparsed body string, so treat this as a synthesis trigger rather than a way to fetch a usable audio file.	Yes — it writes
List models	List speech models available to this key.	No — read only

3 read tools, 1 write tool. Generated from the connector catalogue the product runs on, so it cannot list a tool that does not exist.

What teams hand an agent in ElevenLabs

Content teams hand an agent the voice work around ElevenLabs: List voices and List models for what is available, Get subscription for how much character quota is left, and Text to speech to synthesize. Synthesis is a billed write, so it waits for a person to approve it unless an admin has set this connection to run without asking.

Check remaining character quota before a batch of narration work is promised to anyone.
Pick the right voice id for a project by listing voices with their ids instead of guessing from the dashboard.
Synthesize an agreed script in a chosen voice (billed; after a person approves it)

Before you let it write, or keep out: Text to speech returns raw audio bytes rather than a saved file, so treat it as triggering synthesis -- the usable audio is collected from ElevenLabs, not from the chat. Every approved or unattended call spends quota.

What waits for a person

Reads run on their own. These do not — each one waits in Approvals for an owner or admin unless an admin has set this connection to run writes without asking, and every call toElevenLabs, approved, rejected or unattended, is logged.

Text to speech POST

What connecting ElevenLabs takes

ElevenLabs uses an API key you create in ElevenLabs and paste in once. A workspace admin sets the connection up; the fields are:

API Key

Credentials are encrypted and bound to your workspace, never read back, and every outbound call passes one guarded fetch — the connector security posture sets out exactly how, and the security page covers the platform around it.

Where ElevenLabs fits

Give an agent ElevenLabs work by writing a message in the inbox, or put its tools in a scheduled flow. What the run cost is on the cost breakdown.

Other ai and media integrations: AnythingLLM, AssemblyAI, D-ID. Or see every application agents can connect to.

See it doing your actual work

Open a demo workspace, connect one app, and give an agent a real job. No card, no sales call.

Try the demo See pricing

We reply to every message within one business day.