Telephony and WebRTC

Learn in five minutes

• The W3C WebRTC Recommendation of 13 March 2025 defines APIs so media can be sent to and received from another browser or device.
• Wikipedia's WebRTC page says the API does not include signaling, and that an application may use SIP or another protocol.
• RFC 3261 defines SIP, the Session Initiation Protocol.
• The xAI Speech to Speech page says you can connect via SIP, WebSocket, or LiveKit, and names native G.711 μ-law and A-law support.
• That page says PSTN, contact-center, or PBX calls can be routed into a session. This lab places no call.

WebRTC carries media. SIP is a signaling protocol. Put them in different boxes. Leave the API key off the page.

This section HTML

Visual

Diagram SVGDiagram PNGDiagram HTML

Flow SVGFlow PNGFlow HTML

Two boxes, no call

1. Box 1: WebRTC, media in the browser, from the W3C Recommendation.
2. Box 2: SIP, signaling, from RFC 3261.
3. A note: xAI's page also names WebSocket and LiveKit as ways to connect.
4. Stop. Do not open a socket and do not buy a number.

This section HTML

Quiz

This section HTML

Ecosystem

Signaling

How the ends find each other. WebRTC's Wikipedia page says the media API does not include it.

Sisters: Speech-to-text, Language model, Text-to-speech, WebRTC, SIP.

A cascaded pipeline and a speech-to-speech model are two shapes the LiveKit docs name. The xAI Speech to Speech API is a hosted speech-to-speech session.

Pin the model id, the voice, and the date you read the docs.

Config

• Write the goal in one sentence.
• Name the input and the allowed output.
• Save the trace next to the result.

Troubleshooting

• The answer looks fluent and is wrong. Check whether a source passage actually contains the claim.
• The loop never stops. Set a step cap and stop when the tool result repeats.

This section HTML