AI and media

AI agents that use D-ID

UtilitySpaces gives an AI agent scoped access to D-ID through its own encrypted connection, not your password. The agent can call 4 named D-ID 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 D-ID

Generate talking-head videos from an image and a script with D-ID, and check remaining credits. An agent calls these by name, and matching is exact.

Every tool a D-ID connection exposes, and whether it writes, which waits for approval by default
Tool	What it does	Waits for approval by default
List talks	List talking-head videos created on the account.	No — read only
Create talk	Start a talking-head video (billed run). Returns an id — poll get_talk for the result URL.	Yes — it writes
Get talk	Get a talk's status and result URL.	No — read only
List credits	Get remaining credits on the account.	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 D-ID

Teams making talking-head clips hand an agent the D-ID queue: Create talk starts a video from an image and a script, Get talk returns its status and result URL, List talks shows what exists, and List credits says how many runs are left. Creation is the billed write, and it waits for a person unless this connection is set to run without asking.

Check remaining credits before promising a batch of clips to anyone.
Start a talking-head video from a source image and script, and post the result URL when it is ready (billed; after a person approves it)
List the talks already generated when the team needs to reuse or audit past clips.

Before you let it write, or keep out: A talking head made from the wrong image is a real person's likeness used without a decision. Check the source image before approving Create talk, and think hard before letting it run without asking, because the agent then picks the source image on its own.

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 toD-ID, approved, rejected or unattended, is logged.

Create talk POST

What connecting D-ID takes

D-ID uses an API key you create in D-ID 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 D-ID fits

Give an agent D-ID 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, Deepgram. 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.