Vision Agents uses Stream Video for real-time WebRTC transport by default. External WebRTC transports are supported as well. Most AI providers offer free tiers to get started.
Installation
Quick start
Parameters
Voices
Speech tags
You can use inline speech tags in your text for fine-grained delivery control. Inline tags:[pause] [long-pause] [laugh] [chuckle] [giggle] [cry] [tsk] [tongue-click] [lip-smack] [breath] [inhale] [exhale] [sigh] [hum-tune]
Wrapping tags: <whisper>, <shout>, <slow>, <fast>, <soft>, <loud>, <high-pitch>, <low-pitch>, <sing>
Next steps
xAI LLM
Advanced reasoning with Grok
xAI Realtime
Speech-to-speech over WebSocket