Quick Start

Get your AI agent into a voice meeting in minutes. Pick the integration that fits your setup.

1. Get an API Key

Sign up at chamade.io/dashboard, then create an API key. It starts with chmd_ and is shown only once — store it securely.

2. Choose Your Integration

MCP Server (HTTP — recommended)

For Claude Desktop, Claude Code, Cursor, Windsurf, and any MCP client that supports the Streamable HTTP transport. Drop the snippet below in your MCP config file (.mcp.json, claude_desktop_config.json, .cursor/mcp.json…) and restart the client.

            json
            
        
{
  "mcpServers": {
    "chamade": {
      "type": "http",
      "url": "https://mcp.chamade.io/mcp/",
      "headers": {
        "Authorization": "Bearer chmd_..."
      }
    }
  }
}

Claude Code only: also launch with claude --dangerously-load-development-channels server:chamade --continue on every session to receive push events (incoming calls, DMs) in real time. No flag needed for the tools themselves — they work immediately.

Legacy stdio-only clients (older MCP clients without Streamable HTTP): use the @chamade/mcp-server@3 stdio shim — it's a thin wrapper around mcp-remote that bridges stdio to the same hosted HTTP endpoint. See the full MCP setup guide for the shim config.

Full MCP setup guide →

REST API

For any language or framework. Direct HTTP calls — no MCP client needed. Works great for pure-backend agents, non-LLM orchestration, webhooks, and anything that speaks HTTP.

            bash
            
        
curl -X POST https://chamade.io/api/call \
  -H "X-API-Key: chmd_..." \
  -H "Content-Type: application/json" \
  -d '{"platform":"discord","meeting_url":"https://discord.com/channels/..."}'

Full API reference →

Files & attachments: pass attachments: [{file_id}] on chamade_dm_chat or chamade_call_chat after uploading via POST /api/files (or mint a pre-signed no-auth upload URL via chamade_file_upload_url). Send + receive live on Discord, Telegram, Slack, WhatsApp (incl. voice notes), NC Talk. 25 MB cap. See Files API.

Voice calls — hosted STT/TTS (recommended) or raw-PCM WebSocket

For voice, the recommended path is hosted STT/TTS with BYOK: drop an ElevenLabs or Deepgram key once in dashboard → Voice providers and Chamade runs the whole pipeline on its side using your key. Transcripts arrive as call_transcript events, chamade_call_say speaks into the meeting, and you don't need to touch raw audio. No Chamade charge — you only pay your provider. See Voice providers.

The raw-PCM WebSocket is the alternative — use it when you'd rather run the speech layer in-process (OpenAI Realtime, LiveKit Agents, Pipecat, Deepgram Voice Agent, ElevenLabs, Cartesia, Whisper cascade, …). POST /api/call returns an audio block either way; your host code connects to stream_url and pipes raw PCM both directions.

            json
            
        
{
  "call_id": "abc-123",
  "capabilities": ["audio_in", "audio_out", "read", "write"],
  "audio": {
    "stream_url": "wss://chamade.io/api/call/abc-123/stream",
    "format": "pcm_s16le",
    "sample_rate": 48000,
    "frame_duration_ms": 20,
    "direction": "bidirectional",
    "docs": "https://chamade.io/docs/api#websocket"
  }
}

In BYO-audio mode, your agent's host code (not the LLM itself) opens the stream_url in parallel with MCP/REST, pipes binary PCM frames in both directions between the call and your chosen STT/TTS, and lets the LLM drive the conversation via text.

Audio WebSocket protocol →

3. Connect Your Platforms

Some platforms require setup in the Dashboard before use:

Platform	Setup needed
Discord	Works out of the box (shared bot) or add your own bot
Microsoft Teams	Connect Microsoft account (OAuth)
Google Meet	Connect Google account (OAuth)
Zoom	No setup — just pass a meeting URL
Telegram	Works out of the box or add your own bot
WhatsApp	No setup — invite the bot
Slack	Install the Slack app
Nextcloud Talk	Install addon + connect
SIP / Phone	Activate a phone number or bring your own trunk