Integrations/ElevenLabs

Control what your AI agents do in ElevenLabs.

Let your team build AI agents for ElevenLabs. Bollard AI controls what each one can do, and generating audio stays off by default.

Request early accessSee how it works →
ElevenLabs
Voice Agent
Projects Account areaOffReadFull use
Voices Account areaOffReadFull use
Generation Account areaOffReadFull use
Generate speech
What agents can do

Set what each agent can do across your account.

Each area of ElevenLabs, like projects, voices, or generation, gets one of three levels: Off, Read, or Full use. Anything not allowed is denied, and generating audio is a separate switch.

Off
No access
The agent can't see that part of your account.
Read
Read-only
The agent can read voices and project details in that area. It can't change or generate anything.
Full use
Create and update
The agent can create and update projects in that area.

Some actions stay off until explicitly turned on

Each one uses up your quota, copies a voice, or removes work for good, so it could override the limits set elsewhere.

Generating speechCloning voicesDeleting projects or voices
Set up & manage

Connect once. Manage everyone from there.

Connect once, then control access person by person. No new keys to hand out.

Step 1 · Set up

Connect once, company-wide

An admin connects your company's ElevenLabs a single time. Bollard AI lays out the areas of your account, and anything you don't allow stays out of reach for every agent.

Step 2 · Manage

Control access per person and agent

From one dashboard, set what every person and their agents can reach. Change it any time, with no new keys for anyone.

OffNo access
ReadRead-only
Full useRead, create, and update projects in a single area
Example

A voiceover prep agent.

A voice agent sets up projects and can read your voices, but it can't generate speech or clone a voice.

Projects Account areaOffReadFull use
Voices Account areaOffReadFull use
Generation Account areaOffReadFull use

Manage access

ALLOWEDVoice Agent updated a record in Projects
ALLOWEDVoice Agent read a Voice
BLOCKEDVoice Agent tried to generate speech, denied by default

Monitor activity

The security model

Top-tier security.

Bollard AI is access control for AI agents. It sits between your agents and ElevenLabs, so they never hold your ElevenLabs keys and never reach ElevenLabs directly.

Everything runs through Bollard AI

Agents send their requests to Bollard AI, not to ElevenLabs. Bollard AI checks each one against your rules and passes only the allowed requests through.

Denied by default

Every area starts off-limits, and generating audio is held back on top of that. An agent gets in only where you've allowed it, and anything Bollard AI doesn't recognise is refused and held for review, never waved through on a guess.

Your keys stay sealed

Your ElevenLabs keys are sealed in a vault unique to your company and never shown again. Bollard AI unlocks them only for the instant an allowed request needs it.

Activity you can read

Every attempt is recorded in plain English: who or which agent, what they tried, which project or voice, and the decision. The record is readable and can't be edited after the fact.

Questions

ElevenLabs, answered.

Does connecting ElevenLabs hand Bollard AI your whole account?+
Only the areas you allow. An admin connects your ElevenLabs, and you decide which areas, like projects or voices, each agent can reach. Bollard AI doesn't browse or copy your account. It sits in front of it and checks every request the agents make, passing or blocking each one.
Can an agent generate audio and use up our quota?+
Not unless you turn it on. Generating speech and cloning voices are held off by default, so an agent can set up projects and read voices without ever using your quota, until you explicitly allow it.
Can an agent see more than the person who owns it?+
No. An agent reaches only what its owner reaches. An explicit Off always overrides an inherited permission.
Where do our ElevenLabs keys live?+
Sealed in an encrypted vault, behind a key unique to your company. It's never shown again once connected, and Bollard AI unseals it only for the instant an allowed request needs it.
What happens when an agent tries something it's not allowed to do?+
Bollard AI blocks the request before it reaches ElevenLabs, and the blocked attempt lands in the activity record with the reason.
How do we connect ElevenLabs?+
An admin connects the company's ElevenLabs once. Bollard AI seals the connection and lays out the areas of your account to set rules for. From then on, all management happens in the Bollard AI dashboard.
Early access

Put your team's agents to work in ElevenLabs, without the risk.

We're onboarding our first development partners now. Tell us about your setup and we'll be in touch.

Request early accessAll integrations →