Deepgram Voice Agent API
The Deepgram Voice Agent API is an end-to-end solution that combines speech-to-text, LLM orchestration, and text-to-speech into a single real-time API. It simplifies the development of conversational voice agents by eliminating the need to stitch together multiple services. The API includes built-in barge-in detection, turn-taking prediction, function calling, and mid-session control to ensure smooth, natural conversations without pauses or interruptions.
Deepgram Voice Agent API is one of 12 APIs that Deepgram publishes on the APIs.io network, described by an AsyncAPI event-driven specification.
Tagged areas include Conversational AI, Real-Time, Voice Agent, and Voice AI. The published artifact set on APIs.io includes API documentation and an AsyncAPI specification.
This event API exposes 2 operations across 1 channel, and defines 31 schemas. It is described by AsyncAPI 2.6.0, at version 1.0.
The API connects through a single server, wss://agent.deepgram.com/v1/agent/converse (wss).
Metadata
The identity and technical contract details declared by the specification.
Channels & Operations 2
Across 1 channel, the API surfaces 2 operations. Each is listed below with its action, channel, parameters, and response codes.
Messages & Schemas 31
The contract defines 31 schemas that model the data carried by its messages. The most detailed are SettingsPayload (4 properties), AgentStartedSpeakingPayload (4 properties), FunctionCallRequestPayload (4 properties), ConversationTextPayload (3 properties). Each schema is shown below with its type and property counts.
Specification
The full machine-readable AsyncAPI contract behind this narrative.
Source
More from Deepgram 11
Other APIs Deepgram publishes across the network.
This is an independent, third-party profile of Deepgram Voice Agent API, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.
The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.
Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.
info@apievangelist.com
·
Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and
you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.