Docs

Appearance

RymiVoice Agent API

~400ms native audio · 5 AI providers · MCP-enabled. Build voice agents that sound human, in any language, with one API.

Get API key →
Quickstart
Open Studio →

Start a call in 30 seconds ​

bash
curl https://api.rymi.live/v1/calls \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "agent_id": "agt_123",
    "participants": [
      { "transport": "pstn", "identity": "+15551234567",
        "from_number": "+15559876543" }
    ]
  }'
typescript
import { Rymi } from '@rymi/node';

const rymi = new Rymi();
const call = await rymi.calls.create({
  agent_id: 'agt_123',
  participants: [{
    transport: 'pstn',
    identity: '+15551234567',
    from_number: '+15559876543'
  }]
});
python
from rymi import Rymi

rymi = Rymi()
call = rymi.calls.create(
    agent_id="agt_123",
    participants=[{
        "transport": "pstn",
        "identity": "+15551234567",
        "from_number": "+15559876543"
    }]
)
json
{
  "mcpServers": {
    "rymi": {
      "type": "http",
      "url": "https://mcp.rymi.live/",
      "headers": {
        "Authorization": "Bearer rymi_your_secret_key"
      }
    }
  }
}

What do you want to build? ​

📞
Outbound calls
Queue up to 500 PSTN calls in one request. Built-in retry, health monitoring, variables.
Quickstart →
☎️
Inbound agent
BYOC a Plivo/Twilio/Vonage number and route incoming calls to a voice agent.
Integrate telephony →
🌐
Browser widget
Drop a WebRTC voice agent into any site with the React SDK. Publishable keys, scoped to an agent.
Embed in browser →
🤖
AI agents via MCP
Let Claude, Cursor, or any MCP client create and manage Rymi voice agents through tool calls.
Set up MCP →
📊
Post-call analysis
Signed webhooks with summaries, sentiment, and structured JSON extraction after every call.
Post-call intelligence →
🔔
Webhook events
HMAC-signed events for call lifecycle, intelligence-ready, and DNC flags.
Webhook reference →

Client libraries ​

Node.jsnpm i @rymi/nodePythonpip install rymiReactnpm i @rymi/reactBrowsernpm i @rymi/webMCP newmcp.rymi.live

Recent updates ​

Apr 2026
MCP server — any MCP-capable AI client (Claude Desktop, Claude Code, Cursor, or a Rymi voice agent itself) can now create and manage voice agents. Read the docs →
Apr 2026
Flat-diff change-set API — validate and apply typed config updates via POST /v1/agents/apply-changes. See reference →
Apr 2026
AI-powered agent drafts — generate a full voice agent config from a one-line description with POST /v1/agents/generate.