Data & AI · wired today

ElevenLabs, wired into your agent workforce

Models and datasets are infrastructure now, and agents need eyes on them. The ElevenLabs connector is one of 222 executable connectors and gives agents 5 tools, with the credential held in the vault and every call receipted.

Connecting ElevenLabs takes one credential

You provide API key from your ElevenLabs account; Quox sends it as an API key sent as a header. The credential is stored encrypted in the vault and resolved just-in-time, so agents use it without ever seeing it.

Where to get it: ElevenLabs's own API documentation ↗ covers creating and scoping the credential.

What agents can run against ElevenLabs

get_user

Get the ElevenLabs account behind this API key: subscription tier and remaining character quota (used and limit). The cheap balance read and the spec's auth-proving test call

list_voices

List voices available to this account, from ElevenLabs's shared library and any cloned voices, with id, name and category

list_models

List the text-to-speech models available on this account, with id, name and supported languages

get_history

List past generations (text-to-speech, dubbing, etc) on this account, most recent first, with the voice used and generation date

text_to_speech

Generate speech audio from text using a specific voice. This spends the account's character quota and returns raw audio bytes (not JSON), so it is HITL-gated and never fired by the shape-proof harness (write:true means blind proof always SKIPs it; a real credential would also need --include-writes)

How proven is this?

This connector was blind shape-proven against the real ElevenLabs API: every endpoint it declares answered measurably differently from a deliberately bogus control request, without any account or credential involved. It is Beta: proven against the live API surface, not yet run with a real credential.

Credentialed The vault stores, tests and just-in-time resolves its credential; agents never see the secret.
Approvable Its write tools execute only after a human approves them in the inbox.
Agent-owned No dedicated agent owns it yet; the orchestrator can drive it on request.
Schedulable Not yet exposed in the workflow builder; that integration is on the connector roadmap.
Evidenced Per-call evidence envelopes are on the roadmap; vault credential use is already receipted.

ElevenLabs integration FAQ

What can Quox agents do with ElevenLabs?

Agents can run 5 tools against ElevenLabs: get user, list voices, list models, get history, text to speech. Every call is receipted in the evidence trail.

What does the ElevenLabs integration need?

You provide API key from your ElevenLabs account; Quox sends it as an API key sent as a header. The credential is stored encrypted in the vault and resolved just-in-time, so agents use it without ever seeing it.

Do agents see my ElevenLabs credentials?

No. Credentials live encrypted in the Quox vault and are resolved server-side at call time. Agents invoke tools; they never receive the underlying secret.

How proven is the ElevenLabs connector?