Self-hosted audio protocol

In Self-Hosted audio mode (config.type: "audio" on the Self-Hosted configuration), Dial connects the raw call audio to a WebSocket server you host. Where the LLM protocol sends you transcripts and asks for text turns — with Dial running speech-to-text and text-to-speech — the audio protocol hands you the sound itself, both directions. Your server brings the entire voice stack: a speech-to-speech model (OpenAI Realtime, Gemini Live, …) or your own STT → LLM → TTS chain.

These pages are the complete contract — you can build a conformant server from them alone. The SDKs ship a ready-made server helper (signature verification, frame codec, keepalive) so you start from handlers, not from a WebSocket loop.

Connection

Dial opens one WebSocket per call to your configured URL with the call id appended to the path:

wss://<your-host>/<your-path>/<call_id>

call_id is Dial’s own call identifier — stable for the life of the call, and the only call identifier you ever receive. If the connection drops mid-call, Dial reconnects to the same path and sends a fresh call_connected with reconnect: true (see Reconnection).

With a Pipecat Cloud target, Dial connects to Pipecat’s generic WebSocket with a fresh single-use token instead, so the path carries no call_id. Read it from call_connected, or from the /start body (args.body).

All frames are JSON text, discriminated by a type field, snake_case throughout. Audio rides inside media frames as base64.

Authentication

Identical to the LLM protocol: every connection carries

X-Dial-Signature: t=<unix_seconds>,v1=<hex_signature>

where hex_signature is HMAC-SHA256(secret, "<t>.<call_id>") as a hex digest, with the signing secret from your Self-Hosted configuration. Verify on connect with a constant-time comparison and reject stale timestamps. The SDK helpers do this for you.

A Pipecat Cloud target is authenticated by Pipecat’s single-use token instead. Dial still sends the header, but Pipecat may not pass it on to your bot, so don’t depend on it there.

Audio formats

The audio encoding in each direction is set on your Self-Hosted configuration and echoed in every call_connected frame — there is no in-band renegotiation. Both directions support the same five formats:

All audio is mono. Dial sends caller audio in your inbound format in ~20 ms frames; you send agent audio in your outbound format, any chunking (Dial buffers and paces playback).

Message types

From Dial → your server:

From your server → Dial:

Both ways: ping_pong — the keepalive: Dial pings every ~2 s; echo it back. Miss enough pongs and Dial treats the link as dead and reconnects.

Reconnection

If the socket drops mid-call, the call itself stays up: Dial discards caller audio while disconnected (never replays it — the conversation is live), and re-dials your endpoint with backoff for up to ~15 seconds. The new connection starts with call_connected carrying reconnect: true — restore your per-call state keyed by call_id and resume streaming. For a Pipecat Cloud target, every reconnect uses a new token (and may reach a different agent instance, so keep per-call state outside the process). If reconnection fails past the budget, the call ends and your Call record reflects it. After you send end_call, reconnect attempts for that call are refused.