Skip to main content

Place calls

One POST puts an AI agent on the phone. It returns when the INVITE is on its way, not when someone answers.

Get the report back

Every finished interaction is POSTed to your endpoint, signed and complete — no follow-up GET.

One key, one customer

A vdx_live_ key carries its own tenant. There is no tenant parameter to get wrong.
Base URL: https://apiv2.vodex.ai/v1

​
What this covers

Everything a customer’s own systems integrate with: assistants, telephony (numbers, trunks, carrier integrations), calls and recordings, batch dialing, the SMS channel, and outbound webhooks. It is deliberately a subset. Account and console-only routes, platform provisioning, Vodex support operations, and the endpoints other systems call inward (carrier delivery receipts, the agent worker, cron) are not part of the published surface. The data plane — the LiveKit SFU, SIP, and the agent worker — is not an HTTP API and is not described here. A call reaches the worker over LiveKit, with its config carried in participant metadata or read from the config snapshot this API publishes.

​
Response shapes

Resources come back flat, at the top level — there is no envelope object. Collections vary by the age of the endpoint:
  • Newer lists are { "<plural>": [ … ], "total": n, "limit": n, "offset": n } — calls, batches, rows, attempts, messages.
  • Older lists return a bare JSON array: /phone-numbers, /sip-trunks, /integrations, /carriers, /console/assistants, /sms/configurations.
Deletes and side-effecting no-content operations return { "ok": true }.

​
Errors

A flat string, not a coded object — the HTTP status is the machine signal. The one exception is quota exhaustion (402), which adds a stable code: "quota_exhausted" plus the counters the console renders.

​
Pagination

?limit= and ?offset=, with total in the body. Defaults and ceilings differ per endpoint (calls 25/100, batch rows 50/500, attempts 100/500) and are stated on each operation.

​
Conventions

​
Customers, tenants and workspaces

Three words, and they are not interchangeable. Customer is the product word — what a human calls the account, and what the console shows. Tenant is the same thing’s identity on the wire and in storage: tenantId on every response. A workspace is a third thing, and not a synonym for either. Tenancy is mapped at the customer level deliberately: integrations (carrier, SMS, provider credentials) live above the workspaces that use them, so mapping workspaces to tenants would fragment one customer’s telephony across tenants that then have to share credentials. A workspace is therefore a label inside the tenant (externalWorkspaceRef) — for filtering and attribution, never isolation.
Anything that must not be shared between one customer’s workspaces needs its own tenant.