Skip to main content

Overview

The Voice AI API provides a complete outbound and inbound voice calling platform. It handles campaign dialing, real-time multilingual conversation via AI personas, live transcript streaming, call recording, and post-call structured extraction.

Base URLs​

APIBase pathPurpose
Developer API (v1)https://api.nextneural.ai/v1Public REST API — use this for all integrations
Internal API/api/voiceDashboard-facing; requires Firebase token

All developer integrations should use the /v1 base URL with an API key.

How it fits together​

Voice Agent  ──►  Campaign (Flow)  ──►  Contacts  ──►  Calls
│ │
└─ AI persona, voice, prompt └─► Webhooks, Transcripts
  1. Voice Agents define the AI persona — name, voice, language, and prompt
  2. Campaigns tie an agent to a contact list and a telephony number
  3. Contacts are the people being called (with metadata for lead targeting)
  4. Calls are placed by launching a campaign or triggering a single call via API
  5. Webhooks deliver real-time events (call.started, call.ended, call.transcript_ready)

Rate limits​

The platform applies a default of 100 requests per minute per API key. Write endpoints and telephony-trigger endpoints have tighter limits noted inline on each endpoint page. Exceeding a limit returns 429 Too Many Requests.

See the full Rate Limit Reference →