Skip to main content
Docs
Search
Search...
⌘
K
to ask AI
GitHub
Ask AI
Introduction
Introduction
Build Agents
Build Agents
Agent Frontends
Agent Frontends
Test & Evaluate
Test & Evaluate
Telephony
Telephony
Robotics
Robotics
WebRTC Transport
WebRTC Transport
Manage & Deploy
Manage & Deploy
References
References
Search
Search...
⌘
K
to ask AI
Ask AI
Introduction
Introduction
Build Agents
Build Agents
Get Started
Introduction
Voice AI quickstart
Agent Builder
Agent Console
Agent Embed Widget
Prompting guide
Multimodality
Overview
Speech & audio
Text & transcriptions
Modality-aware instructions
Images & video
Logic & Structure
Overview
Agent sessions
Chat context
Tasks & task groups
Workflows
Patterns
Tool definition & use
Pipeline nodes & hooks
Turn detection & interruptions
Agents & handoffs
External data & RAG
Fallback strategies
Prebuilt components
Prebuilt tasks
Prebuilt tools
Agent Server
Overview
Startup modes
Server lifecycle
Agent dispatch
Job lifecycle
Server options
Models
Overview
Pipeline types
LiveKit Inference
LLM
STT
TTS
Overview
Cartesia
Deepgram
Fish Audio
Gradium
Inworld
Rime
SpaceXAI
Additional models
AsyncAI
Amazon Polly
Azure AI Speech
Azure OpenAI
Baseten
Bland
Camb.ai
ElevenLabs
Gemini
Gnani
Google Cloud
Groq
Hume
Kokoro
LMNT
MiniMax
Mistral AI
Murf AI
Neuphonic
Nvidia
OpenAI
Resemble AI
Respeecher
Sarvam
Simplismart
SLNG
Smallest AI
Soniox
Speechify
Speechmatics
Spitch
Capabilities
Realtime
Virtual avatar
Partner spotlight
OpenAI
Google
Azure
AWS
SpaceXAI
Groq
Cerebras
Reference
Agents framework
Turn handling options
Events and error handling
Agent dispatch service API
LiveKit CLI
Inference LLM parameters
Agent Frontends
Agent Frontends
Test & Evaluate
Test & Evaluate
Telephony
Telephony
Robotics
Robotics
WebRTC Transport
WebRTC Transport
Manage & Deploy
Manage & Deploy
References
References
X
YouTube
Slack
Get Started
Introduction
Voice AI quickstart
Agent Builder
Agent Console
Agent Embed Widget
Prompting guide
Multimodality
Overview
Speech & audio
Text & transcriptions
Modality-aware instructions
Images & video
Logic & Structure
Overview
Agent sessions
Chat context
Tasks & task groups
Workflows
Patterns
Tool definition & use
Pipeline nodes & hooks
Turn detection & interruptions
Agents & handoffs
External data & RAG
Fallback strategies
Prebuilt components
Prebuilt tasks
Prebuilt tools
Agent Server
Overview
Startup modes
Server lifecycle
Agent dispatch
Job lifecycle
Server options
Models
Overview
Pipeline types
LiveKit Inference
LLM
STT
TTS
Overview
Cartesia
Deepgram
Fish Audio
Gradium
Inworld
Rime
SpaceXAI
Additional models
AsyncAI
Amazon Polly
Azure AI Speech
Azure OpenAI
Baseten
Bland
Camb.ai
ElevenLabs
Gemini
Gnani
Google Cloud
Groq
Hume
Kokoro
LMNT
MiniMax
Mistral AI
Murf AI
Neuphonic
Nvidia
OpenAI
Resemble AI
Respeecher
Sarvam
Simplismart
SLNG
Smallest AI
Soniox
Speechify
Speechmatics
Spitch
Capabilities
Realtime
Virtual avatar
Partner spotlight
OpenAI
Google
Azure
AWS
SpaceXAI
Groq
Cerebras
Reference
Agents framework
Turn handling options
Events and error handling
Agent dispatch service API
LiveKit CLI
Inference LLM parameters