What is the difference between the REST API and the MCP server?

The REST API is for programmatic server-to-server calls — trigger briefing generation, retrieve MP3 URLs, manage webhooks, integrate with your backend. The MCP server is for AI agents — let Claude, GPT-4, or any MCP-compatible model call ListenBrief tools directly.

What authentication method does the API use?

Bearer token. Generate an API key in your ListenBrief dashboard. Prefix test_ for sandbox, lb_ for production. Keys can be scoped to read-only, generate-only, or full access.

Is there a webhook system for async briefing delivery?

Yes. Register a webhook URL and ListenBrief will POST a signed JSON payload when briefing generation completes. Payloads include briefing ID, status, MP3 URL, and summary.

Can I see the OpenAPI spec before signing up?

Yes. The full OpenAPI 3.1 spec is at https://listenbrief.com/developer/openapi.json — no login required. Interactive documentation is at developer.listenbrief.com/api.

What is the SLA for briefing generation?

Briefings are generated within 2-5 minutes of request. Scheduled morning briefings complete by 6:10 AM UTC. Priority generation (Power/Enterprise) completes in under 90 seconds.

AI Briefing API — REST + MCP for Your Stack

Most AI APIs are text-only. ListenBrief is built for audio — and the API surface reflects that. The REST API is your backend integration layer: create profiles, add sources, trigger briefings, retrieve MP3 URLs, register webhooks. The MCP server is your AI agent integration layer: give any MCP-compatible model the ability to use ListenBrief directly. Both share the same authentication, same data model, and same underlying generation pipeline.

REST API: 17 endpoints

POST /api/v1/profiles

GET /api/v1/profiles/:id

PATCH /api/v1/profiles/:id

POST /api/v1/sources

GET /api/v1/sources

DELETE /api/v1/sources/:id

POST /api/v1/briefings

GET /api/v1/briefings/:id

GET /api/v1/briefings/:id/audio

GET /api/v1/briefings/:id/transcript

GET /api/v1/briefings/:id/summary

POST /api/v1/schedules

PATCH /api/v1/schedules/:id

DELETE /api/v1/schedules/:id

POST /api/v1/webhooks

GET /api/v1/webhooks

DELETE /api/v1/webhooks/:id

MCP server: 10 tools

The MCP server at https://listenbrief.com/mcp/v1 exposes 10 tools over JSON-RPC 2.0: create_briefing_profile, update_briefing_profile, add_source, generate_briefing, get_latest_briefing, get_briefing_audio, get_briefing_transcript, schedule_briefing, pause_briefing, resume_briefing.

Works with Claude Desktop, Continue, Cursor, and any MCP-compatible client. See the MCP quickstart guide.

Async briefing generation with webhooks

Briefing generation is asynchronous (takes 2-5 minutes). The recommended pattern:

POST /api/v1/briefings to trigger generation, receive a briefing ID immediately
Register a webhook (POST /api/v1/webhooks) to receive completion notification
When the webhook fires, fetch the MP3 URL from GET /api/v1/briefings/:id/audio

Webhook payloads are signed with HMAC-SHA256. Verify the signature before processing. See webhook documentation.

▶

Example output — what the API generates

AI Investor Briefing — 3-minute example MP3

Authentication and key scoping

All requests use Bearer token authentication. API keys are generated in your ListenBrief dashboard and support fine-grained scoping:

lb_* — production key, full access
test_* — sandbox key, no quota consumed, simulated responses
Read-only scope: retrieve briefings and transcripts without generation access
Generate-only scope: create briefings without profile or source management access

Start without signing up: Browse the full OpenAPI 3.1 spec at listenbrief.com/developer/openapi.json and the interactive docs at developer.listenbrief.com — no account needed.

AI briefing API: REST + MCP for your stack

REST API: 17 endpoints

MCP server: 10 tools

Async briefing generation with webhooks

Authentication and key scoping

Frequently asked questions

Build audio intelligence into your stack.