For AI agents: a documentation index is available at the root level at /llms.txt and /llms-full.txt. Append /llms.txt to any URL for a page-level index, or .md for the markdown version of any page.
Ask AIPlaygroundLoginFree API Key
HomeAPI ReferenceVoice AgentSpeech-to-TextText-to-SpeechIntelligenceSelf-Hosted Deployments
HomeAPI ReferenceVoice AgentSpeech-to-TextText-to-SpeechIntelligenceSelf-Hosted Deployments
  • Get Started
    • Overview
    • Build a Voice Agent
    • Feature Overview
    • Template Apps
  • Configure
    • Overview
    • STT Models
    • LLM Models
    • TTS Models
    • Media Inputs & Outputs
    • Prompting Voice Agents
    • Multilingual Voice Agents
    • Maintaining Context
    • Reusable Agent Configurations
  • Build
    • Multi-Agent Architecture
  • Connect
  • Controls
      • Overview
      • Welcome
      • Settings Applied
      • Conversation Text
      • User Started Speaking
      • Agent Thinking
      • Acknowledgements
      • Agent Audio Done
      • Errors & Warnings
      • History
  • Optimize
    • Voice Agent TTS Controls
    • Message Flow
    • Audio & Playback
    • Audio Preprocessing & Barge-In
    • Adaptive Echo Cancellation
  • Resources
    • SDKs
    • UI Components
    • API Reference
LogoLogo
Ask AIPlaygroundLoginFree API Key
On this page
  • PromptUpdated
  • SpeakUpdated
  • ThinkUpdated
ControlsOutputs: Server Events

Acknowledgements

Server confirms that an Update* message has been applied.

Was this page helpful?
Previous

Agent Audio Done

The server sends AgentAudioDone after streaming the final audio chunk for an agent utterance.

Next
Built with
Voice Agent

When the client sends an UpdatePrompt, UpdateSpeak, or UpdateThink message, the server applies the change and replies with a corresponding acknowledgement event. The new configuration takes effect immediately and applies to every subsequent request.

You do not need to handle these events unless you want to verify that an update landed.

PromptUpdated

The server sends PromptUpdated after applying an UpdatePrompt message.

JSON
1{
2 "type": "PromptUpdated"
3}

SpeakUpdated

The server sends SpeakUpdated after applying an UpdateSpeak message.

JSON
1{
2 "type": "SpeakUpdated"
3}

ThinkUpdated

The server sends ThinkUpdated after applying an UpdateThink message. Because UpdateThink replaces the entire Think provider configuration (model, prompt, endpoint, and functions), ThinkUpdated confirms that the full replacement landed.

JSON
1{
2 "type": "ThinkUpdated"
3}