Feature Overview — Deepgram

You will need to migrate to the new V1 Agent API to continue to use the Voice Agent API. Please refer to the Voice Agent API Migration Guide for more information.

Voice Selection

Voice Selection
Deepgram TTS Voice Models
Third Party TTS Voice Models

Supported LLM Models

Models
LLM Models

Inputs: Client Messages

Feature
Settings
Update Speak
Inject Agent Message
Agent Keep Alive

Outputs: Server Events

Feature
Welcome
Settings Applied
Conversation Text
User Started Speaking
Agent Thinking
Prompt Updated
Speak Updated
Agent Audio Done
Agent Errors
Agent Warnings

Input / Output Events

Feature
Function Call Request
Function Call Response

Rate Limits

For information on Deepgram’s Concurrency Rate Limits, refer to our API Rate Limits Documentation.

Deepgram Self-Hosted

Having challenges with performance and latency? Check out Deepgram’s Self-Hosted Solution to get the benefits of running your own hosted instance of Deepgram.